Authors: Yushi Lan, Feitong Tan, Di Qiu, Qiangeng Xu, Kyle Genova, Zeng Huang, Sean Fanello, Rohit Pandey, Thomas Funkhouser, Chen Change Loy, Yinda Zhang
We present a novel framework for generating photorealistic 3D human head and subsequently manipulating and reposing them with remarkable flexibility. The proposed approach leverages an implicit function representation of 3D human heads, employing 3D Gaussians anchored on a parametric face model. To enhance representational capabilities and encode spatial information, we embed a lightweight tri-plane payload within each Gaussian rather than directly storing color and opacity. Additionally, we parameterize the Gaussians in a 2D UV space via a 3DMM, enabling effective utilization of the diffusion model for 3D head avatar generation. Our method facilitates the creation of diverse and realistic 3D human heads with fine-grained editing over facial features and expressions. Extensive experiments demonstrate the effectiveness of our method.
Authors: Brian Gordon, Yonatan Bitton, Yonatan Shafir, Roopal Garg, Xi Chen, Dani Lischinski, Daniel Cohen-Or, Idan Szpektor
While existing image-text alignment models reach high quality binary assessments, they fall short of pinpointing the exact source of misalignment. In this paper, we present a method to provide detailed textual and visual explanation of detected misalignments between text-image pairs. We leverage large language models and visual grounding models to automatically construct a training set that holds plausible misaligned captions for a given image and corresponding textual explanations and visual indicators. We also publish a new human curated test set comprising ground-truth textual and visual misalignment annotations. Empirical results show that fine-tuning vision language models on our training set enables them to articulate misalignments and visually indicate them within images, outperforming strong baselines both on the binary alignment classification and the explanation generation tasks. Our method code and human curated test set are available at: https://mismatch-quest.github.io/
Authors: Chowdhury Sadman Jahan, Andreas Savakis
Open Set Domain Adaptation (OSDA) aims to adapt a model trained on a source domain to a target domain that undergoes distribution shift and contains samples from novel classes outside the source domain. Source-free OSDA (SF-OSDA) techniques eliminate the need to access source domain samples, but current SF-OSDA methods utilize only the known classes in the target domain for adaptation, and require access to the entire target domain even during inference after adaptation, to make the distinction between known and unknown samples. In this paper, we introduce Unknown Sample Discovery (USD) as an SF-OSDA method that utilizes a temporally ensembled teacher model to conduct known-unknown target sample separation and adapts the student model to the target domain over all classes using co-training and temporal consistency between the teacher and the student. USD promotes Jensen-Shannon distance (JSD) as an effective measure for known-unknown sample separation. Our teacher-student framework significantly reduces error accumulation resulting from imperfect known-unknown sample separation, while curriculum guidance helps to reliably learn the distinction between target known and target unknown subspaces. USD appends the target model with an unknown class node, thus readily classifying a target sample into any of the known or unknown classes in subsequent post-adaptation inference stages. Empirical results show that USD is superior to existing SF-OSDA methods and is competitive with current OSDA models that utilize both source and target domains during adaptation.
Authors: Shaoan Xie, Yang Zhao, Zhisheng Xiao, Kelvin C.K. Chan, Yandong Li, Yanwu Xu, Kun Zhang, Tingbo Hou
This study introduces Text-Guided Subject-Driven Image Inpainting, a novel task that combines text and exemplar images for image inpainting. While both text and exemplar images have been used independently in previous efforts, their combined utilization remains unexplored. Simultaneously accommodating both conditions poses a significant challenge due to the inherent balance required between editability and subject fidelity. To tackle this challenge, we propose a two-step approach DreamInpainter. First, we compute dense subject features to ensure accurate subject replication. Then, we employ a discriminative token selection module to eliminate redundant subject details, preserving the subject's identity while allowing changes according to other conditions such as mask shape and text prompts. Additionally, we introduce a decoupling regularization technique to enhance text control in the presence of exemplar images. Our extensive experiments demonstrate the superior performance of our method in terms of visual quality, identity preservation, and text control, showcasing its effectiveness in the context of text-guided subject-driven image inpainting.
Authors: Shao-Yu Chang, Hwann-Tzong Chen, Tyng-Luh Liu
We present a diffusion-based video editing framework, namely DiffusionAtlas, which can achieve both frame consistency and high fidelity in editing video object appearance. Despite the success in image editing, diffusion models still encounter significant hindrances when it comes to video editing due to the challenge of maintaining spatiotemporal consistency in the object's appearance across frames. On the other hand, atlas-based techniques allow propagating edits on the layered representations consistently back to frames. However, they often struggle to create editing effects that adhere correctly to the user-provided textual or visual conditions due to the limitation of editing the texture atlas on a fixed UV mapping field. Our method leverages a visual-textual diffusion model to edit objects directly on the diffusion atlases, ensuring coherent object identity across frames. We design a loss term with atlas-based constraints and build a pretrained text-driven diffusion model as pixel-wise guidance for refining shape distortions and correcting texture deviations. Qualitative and quantitative experiments show that our method outperforms state-of-the-art methods in achieving consistent high-fidelity video-object editing.
Authors: Yuhang Lu, Xinge Zhu, Tai Wang, Yuexin Ma
Occupancy prediction has increasingly garnered attention in recent years for its fine-grained understanding of 3D scenes. Traditional approaches typically rely on dense, regular grid representations, which often leads to excessive computational demands and a loss of spatial details for small objects. This paper introduces OctreeOcc, an innovative 3D occupancy prediction framework that leverages the octree representation to adaptively capture valuable information in 3D, offering variable granularity to accommodate object shapes and semantic regions of varying sizes and complexities. In particular, we incorporate image semantic information to improve the accuracy of initial octree structures and design an effective rectification mechanism to refine the octree structure iteratively. Our extensive evaluations show that OctreeOcc not only surpasses state-of-the-art methods in occupancy prediction, but also achieves a 15%-24% reduction in computational overhead compared to dense-grid-based methods.
Authors: Linze Li, Sunqi Fan, Hengjun Pu, Zhaodong Bing, Yao Tang, Tianzhu Ye, Tong Yang, Liangyu Chen, Jiajun Liang
Over recent years, diffusion models have facilitated significant advancements in video generation. Yet, the creation of face-related videos still confronts issues such as low facial fidelity, lack of frame consistency, limited editability and uncontrollable human poses. To address these challenges, we introduce a facial animation generation method that enhances both face identity fidelity and editing capabilities while ensuring frame consistency. This approach incorporates the concept of an anchor frame to counteract the degradation of generative ability in original text-to-image models when incorporating a motion module. We propose two strategies towards this objective: training-free and training-based anchor frame methods. Our method's efficacy has been validated on multiple representative DreamBooth and LoRA models, delivering substantial improvements over the original outcomes in terms of facial fidelity, text-to-image editability, and video motion. Moreover, we introduce conditional control using a 3D parametric face model to capture accurate facial movements and expressions. This solution augments the creative possibilities for facial animation generation through the integration of multiple control signals. For additional samples, please visit https://anonymous.4open.science/r/FAAC.
Authors: Xuanimng Cui, Alejandro Aparcedo, Young Kyun Jang, Ser-Nam Lim
Recent advances in instruction tuning have led to the development of State-of-the-Art Large Multimodal Models (LMMs). Given the novelty of these models, the impact of visual adversarial attacks on LMMs has not been thoroughly examined. We conduct a comprehensive study of the robustness of various LMMs against different adversarial attacks, evaluated across tasks including image classification, image captioning, and Visual Question Answer (VQA). We find that in general LMMs are not robust to visual adversarial inputs. However, our findings suggest that context provided to the model via prompts, such as questions in a QA pair helps to mitigate the effects of visual adversarial inputs. Notably, the LMMs evaluated demonstrated remarkable resilience to such attacks on the ScienceQA task with only an 8.10% drop in performance compared to their visual counterparts which dropped 99.73%. We also propose a new approach to real-world image classification which we term query decomposition. By incorporating existence queries into our input prompt we observe diminished attack effectiveness and improvements in image classification accuracy. This research highlights a previously under-explored facet of LMM robustness and sets the stage for future work aimed at strengthening the resilience of multimodal systems in adversarial environments.
Authors: Zixuan Gong, Qi Zhang, Duoqian Miao, Guangyin Bao, Liang Hu
Research in decoding visual information from the brain, particularly through the non-invasive fMRI method, is rapidly progressing. The challenge arises from the limited data availability and the low signal-to-noise ratio of fMRI signals, leading to a low-precision task of fMRI-to-image retrieval. State-of-the-art MindEye remarkably improves fMRI-to-image retrieval performance by leveraging a deep MLP with a high parameter count orders of magnitude, i.e., a 996M MLP Backbone per subject, to align fMRI embeddings to the final hidden layer of CLIP's vision transformer. However, significant individual variations exist among subjects, even within identical experimental setups, mandating the training of subject-specific models. The substantial parameters pose significant challenges in deploying fMRI decoding on practical devices, especially with the necessitating of specific models for each subject. To this end, we propose Lite-Mind, a lightweight, efficient, and versatile brain representation network based on discrete Fourier transform, that efficiently aligns fMRI voxels to fine-grained information of CLIP. Our experiments demonstrate that Lite-Mind achieves an impressive 94.3% fMRI-to-image retrieval accuracy on the NSD dataset for Subject 1, with 98.7% fewer parameters than MindEye. Lite-Mind is also proven to be able to be migrated to smaller brain datasets and establishes a new state-of-the-art for zero-shot classification on the GOD dataset. The code is available at https://github.com/gongzix/Lite-Mind.
Authors: Luigi Riz, Cristiano Saltori, Yiming Wang, Elisa Ricci, Fabio Poiesi
The task of Novel Class Discovery (NCD) in semantic segmentation entails training a model able to accurately segment unlabelled (novel) classes, relying on the available supervision from annotated (base) classes. Although extensively investigated in 2D image data, the extension of the NCD task to the domain of 3D point clouds represents a pioneering effort, characterized by assumptions and challenges that are not present in the 2D case. This paper represents an advancement in the analysis of point cloud data in four directions. Firstly, it introduces the novel task of NCD for point cloud semantic segmentation. Secondly, it demonstrates that directly transposing the only existing NCD method for 2D image semantic segmentation to 3D data yields suboptimal results. Thirdly, a new NCD approach based on online clustering, uncertainty estimation, and semantic distillation is presented. Lastly, a novel evaluation protocol is proposed to rigorously assess the performance of NCD in point cloud semantic segmentation. Through comprehensive evaluations on the SemanticKITTI, SemanticPOSS, and S3DIS datasets, the paper demonstrates substantial superiority of the proposed method over the considered baselines.
Authors: Gangwei Xu, Shujun Chen, Hao Jia, Miaojie Feng, Xin Yang
The full 4D cost volume in Recurrent All-Pairs Field Transforms (RAFT) or global matching by Transformer achieves impressive performance for optical flow estimation. However, their memory consumption increases quadratically with input resolution, rendering them impractical for high-resolution images. In this paper, we present MeFlow, a novel memory-efficient method for high-resolution optical flow estimation. The key of MeFlow is a recurrent local orthogonal cost volume representation, which decomposes the 2D search space dynamically into two 1D orthogonal spaces, enabling our method to scale effectively to very high-resolution inputs. To preserve essential information in the orthogonal space, we utilize self attention to propagate feature information from the 2D space to the orthogonal space. We further propose a radius-distribution multi-scale lookup strategy to model the correspondences of large displacements at a negligible cost. We verify the efficiency and effectiveness of our method on the challenging Sintel and KITTI benchmarks, and real-world 4K ($2160\!\times\!3840$) images. Our method achieves competitive performance on both Sintel and KITTI benchmarks, while maintaining the highest memory efficiency on high-resolution inputs.
Authors: Jiwen Yu, Xiaodong Cun, Chenyang Qi, Yong Zhang, Xintao Wang, Ying Shan, Jian Zhang
Large-scale text-to-video (T2V) diffusion models have great progress in recent years in terms of visual quality, motion and temporal consistency. However, the generation process is still a black box, where all attributes (e.g., appearance, motion) are learned and generated jointly without precise control ability other than rough text descriptions. Inspired by image animation which decouples the video as one specific appearance with the corresponding motion, we propose AnimateZero to unveil the pre-trained text-to-video diffusion model, i.e., AnimateDiff, and provide more precise appearance and motion control abilities for it. For appearance control, we borrow intermediate latents and their features from the text-to-image (T2I) generation for ensuring the generated first frame is equal to the given generated image. For temporal control, we replace the global temporal attention of the original T2V model with our proposed positional-corrected window attention to ensure other frames align with the first frame well. Empowered by the proposed methods, AnimateZero can successfully control the generating progress without further training. As a zero-shot image animator for given images, AnimateZero also enables multiple new applications, including interactive video generation and real image animation. The detailed experiments demonstrate the effectiveness of the proposed method in both T2V and related applications.
Authors: Xinzhou Wang, Yikai Wang, Junliang Ye, Zhengyi Wang, Fuchun Sun, Pengkun Liu, Ling Wang, Kai Sun, Xintong Wang, Bin He
Text-to-3D model adaptations have advanced static 3D model quality, but sequential 3D model generation, particularly for animatable objects with large motions, is still scarce. Our work proposes AnimatableDreamer, a text-to-4D generation framework capable of generating diverse categories of non-rigid objects while adhering to the object motions extracted from a monocular video. At its core, AnimatableDreamer is equipped with our novel optimization design dubbed Canonical Score Distillation (CSD), which simplifies the generation dimension from 4D to 3D by denoising over different frames in the time-varying camera spaces while conducting the distillation process in a unique canonical space shared per video. Concretely, CSD ensures that score gradients back-propagate to the canonical space through differentiable warping, hence guaranteeing the time-consistent generation and maintaining morphological plausibility across different poses. By lifting the 3D generator to 4D with warping functions, AnimatableDreamer offers a novel perspective on non-rigid 3D model generation and reconstruction. Besides, with inductive knowledge from a multi-view consistent diffusion model, CSD regularizes reconstruction from novel views, thus cyclically enhancing the generation process. Extensive experiments demonstrate the capability of our method in generating high-flexibility text-guided 3D models from the monocular video, while also showing improved reconstruction performance over typical non-rigid reconstruction methods. Project page https://AnimatableDreamer.github.io.
Authors: Dongshen Han, Seungkyu Lee, Chaoning Zhang, Heechan Yoon, Hyukmin Kwon, HyunCheol Kim, HyonGon Choo
Single Image Reflection Removal (SIRR) in real-world images is a challenging task due to diverse image degradations occurring on the glass surface during light transmission and reflection. Many existing methods rely on specific prior assumptions to resolve the problem. In this paper, we propose a general reflection intensity prior that captures the intensity of the reflection phenomenon and demonstrate its effectiveness. To learn the reflection intensity prior, we introduce the Reflection Prior Extraction Network (RPEN). By segmenting images into regional patches, RPEN learns non-uniform reflection prior in an image. We propose Prior-based Reflection Removal Network (PRRN) using a simple transformer U-Net architecture that adapts reflection prior fed from RPEN. Experimental results on real-world benchmarks demonstrate the effectiveness of our approach achieving state-of-the-art accuracy in SIRR.
Authors: Friedhelm Hamann, Suman Ghosh, Ignacio Juarez Martinez, Tom Hart, Alex Kacelnik, Guillermo Gallego
Researchers in natural science need reliable methods for quantifying animal behavior. Recently, numerous computer vision methods emerged to automate the process. However, observing wild species at remote locations remains a challenging task due to difficult lighting conditions and constraints on power supply and data storage. Event cameras offer unique advantages for battery-dependent remote monitoring due to their low power consumption and high dynamic range capabilities. We use this novel sensor to quantify a behavior in Chinstrap penguins called ecstatic display. We formulate the problem as a temporal action detection task, determining the start and end times of the behavior. For this purpose, we recorded a colony of breeding penguins in Antarctica during several weeks and labeled event data on 16 nests. The developed method consists of a generator of candidate time intervals (proposals) and a classifier of the actions within them. The experiments show that the event cameras' natural response to motion is effective for continuous behavior monitoring and detection, reaching a mean average precision (mAP) of 58% (which increases to 63% in good weather conditions). The results also demonstrate the robustness against various lighting conditions contained in the challenging dataset. The low-power capabilities of the event camera allows to record three times longer than with a conventional camera. This work pioneers the use of event cameras for remote wildlife observation, opening new interdisciplinary opportunities. https://tub-rip.github.io/eventpenguins/
Authors: Felix Meissen, Johannes Getzner, Alexander Ziller, Georgios Kaissis, Daniel Rueckert
Unsupervised anomaly detection (UAD) alleviates large labeling efforts by training exclusively on unlabeled in-distribution data and detecting outliers as anomalies. Generally, the assumption prevails that large training datasets allow the training of higher-performing UAD models. However, in this work, we show that using only very few training samples can already match - and in some cases even improve - anomaly detection compared to training with the whole training dataset. We propose three methods to identify prototypical samples from a large dataset of in-distribution samples. We demonstrate that by training with a subset of just ten such samples, we achieve an area under the receiver operating characteristics curve (AUROC) of $96.37 \%$ on CIFAR10, $92.59 \%$ on CIFAR100, $95.37 \%$ on MNIST, $95.38 \%$ on Fashion-MNIST, $96.37 \%$ on MVTec-AD, $98.81 \%$ on BraTS, and $81.95 \%$ on RSNA pneumonia detection, even exceeding the performance of full training in $25/67$ classes we tested. Additionally, we show that the prototypical in-distribution samples identified by our proposed methods translate well to different models and other datasets and that using their characteristics as guidance allows for successful manual selection of small subsets of high-performing samples. Our code is available at https://anonymous.4open.science/r/uad_prototypical_samples/
Authors: Mushui Liu, Weijie He, Ziqian Lu, Yunlong Yu
Prompt learning is a powerful technique for transferring Vision-Language Models (VLMs) such as CLIP to downstream tasks. However, the prompt-based methods that are fine-tuned solely with base classes may struggle to generalize to novel classes in open-vocabulary scenarios, especially when data are limited. To address this issue, we propose an innovative approach called SYNC-CLIP that leverages SYNthetiC data for enhancing the generalization capability of CLIP. Based on the observation of the distribution shift between the real and synthetic samples, we treat real and synthetic samples as distinct domains and propose to optimize separate domain prompts to capture domain-specific information, along with the shared visual prompts to preserve the semantic consistency between two domains. By aligning the cross-domain features, the synthetic data from novel classes can provide implicit guidance to rebalance the decision boundaries. Experimental results on three model generalization tasks demonstrate that our method performs very competitively across various benchmarks. Notably, SYNC-CLIP outperforms the state-of-the-art competitor PromptSRC by an average improvement of 3.0% on novel classes across 11 datasets in open-vocabulary scenarios.
Authors: Xuanchi Ren, Jiahui Huang, Xiaohui Zeng, Ken Museth, Sanja Fidler, Francis Williams
We present $\mathcal{X}^3$ (pronounced XCube), a novel generative model for high-resolution sparse 3D voxel grids with arbitrary attributes. Our model can generate millions of voxels with a finest effective resolution of up to $1024^3$ in a feed-forward fashion without time-consuming test-time optimization. To achieve this, we employ a hierarchical voxel latent diffusion model which generates progressively higher resolution grids in a coarse-to-fine manner using a custom framework built on the highly efficient VDB data structure. Apart from generating high-resolution objects, we demonstrate the effectiveness of XCube on large outdoor scenes at scales of 100m$\times$100m with a voxel size as small as 10cm. We observe clear qualitative and quantitative improvements over past approaches. In addition to unconditional generation, we show that our model can be used to solve a variety of tasks such as user-guided editing, scene completion from a single scan, and text-to-3D. More results and details can be found at https://research.nvidia.com/labs/toronto-ai/xcube/.
Authors: Ryan Rubel, Nathan Clark, Andrew Dudash
Despite recent advances in both model architectures and data augmentation, multimodal object detectors still barely outperform their LiDAR-only counterparts. This shortcoming has been attributed to a lack of sufficiently powerful multimodal data augmentation. To address this, we present SurfaceAug, a novel ground truth sampling algorithm. SurfaceAug pastes objects by resampling both images and point clouds, enabling object-level transformations in both modalities. We evaluate our algorithm by training a multimodal detector on KITTI and compare its performance to previous works. We show experimentally that SurfaceAug outperforms existing methods on car detection tasks and establishes a new state of the art for multimodal ground truth sampling.
Authors: Ricardo Gonzalez, Ashirbani Saha, Clinton J.V. Campbell, Peyman Nejat, Cynthia Lokker, Andrew P. Norgan
This paper discusses some overlooked challenges faced when working with machine learning models for histopathology and presents a novel opportunity to support "Learning Health Systems" with them. Initially, the authors elaborate on these challenges after separating them according to their mitigation strategies: those that need innovative approaches, time, or future technological capabilities and those that require a conceptual reappraisal from a critical perspective. Then, a novel opportunity to support "Learning Health Systems" by integrating hidden information extracted by ML models from digitalized histopathology slides with other healthcare big data is presented.
Authors: Zhixing Zhang, Bichen Wu, Xiaoyan Wang, Yaqiao Luo, Luxin Zhang, Yinan Zhao, Peter Vajda, Dimitris Metaxas, Licheng Yu
Recent advances in diffusion models have successfully enabled text-guided image inpainting. While it seems straightforward to extend such editing capability into video domain, there has been fewer works regarding text-guided video inpainting. Given a video, a masked region at its initial frame, and an editing prompt, it requires a model to do infilling at each frame following the editing guidance while keeping the out-of-mask region intact. There are three main challenges in text-guided video inpainting: ($i$) temporal consistency of the edited video, ($ii$) supporting different inpainting types at different structural fidelity level, and ($iii$) dealing with variable video length. To address these challenges, we introduce Any-Length Video Inpainting with Diffusion Model, dubbed as AVID. At its core, our model is equipped with effective motion modules and adjustable structure guidance, for fixed-length video inpainting. Building on top of that, we propose a novel Temporal MultiDiffusion sampling pipeline with an middle-frame attention guidance mechanism, facilitating the generation of videos with any desired duration. Our comprehensive experiments show our model can robustly deal with various inpainting types at different video duration range, with high quality. More visualization results is made publicly available at https://zhang-zx.github.io/AVID/ .
Authors: Ryan Burgert, Xiang Li, Abe Leite, Kanchana Ranasinghe, Michael S. Ryoo
We explore the problem of computationally generating special `prime' images that produce optical illusions when physically arranged and viewed in a certain way. First, we propose a formal definition for this problem. Next, we introduce Diffusion Illusions, the first comprehensive pipeline designed to automatically generate a wide range of these illusions. Specifically, we both adapt the existing `score distillation loss' and propose a new `dream target loss' to optimize a group of differentially parametrized prime images, using a frozen text-to-image diffusion model. We study three types of illusions, each where the prime images are arranged in different ways and optimized using the aforementioned losses such that images derived from them align with user-chosen text prompts or images. We conduct comprehensive experiments on these illusions and verify the effectiveness of our proposed method qualitatively and quantitatively. Additionally, we showcase the successful physical fabrication of our illusions -- as they are all designed to work in the real world. Our code and examples are publicly available at our interactive project website: https://diffusionillusions.com
Authors: Zeyi Sun, Ye Fang, Tong Wu, Pan Zhang, Yuhang Zang, Shu Kong, Yuanjun Xiong, Dahua Lin, Jiaqi Wang
Contrastive Language-Image Pre-training (CLIP) plays an essential role in extracting valuable content information from images across diverse tasks. It aligns textual and visual modalities to comprehend the entire image, including all the details, even those irrelevant to specific tasks. However, for a finer understanding and controlled editing of images, it becomes crucial to focus on specific regions of interest, which can be indicated as points, masks, or boxes by humans or perception models. To fulfill the requirements, we introduce Alpha-CLIP, an enhanced version of CLIP with an auxiliary alpha channel to suggest attentive regions and fine-tuned with constructed millions of RGBA region-text pairs. Alpha-CLIP not only preserves the visual recognition ability of CLIP but also enables precise control over the emphasis of image contents. It demonstrates effectiveness in various tasks, including but not limited to open-world recognition, multimodal large language models, and conditional 2D / 3D generation. It has a strong potential to serve as a versatile tool for image-related tasks.
Authors: Bolin Lai, Xiaoliang Dai, Lawrence Chen, Guan Pang, James M. Rehg, Miao Liu
Generating instructional images of human daily actions from an egocentric viewpoint serves a key step towards efficient skill transfer. In this paper, we introduce a novel problem -- egocentric action frame generation. The goal is to synthesize the action frame conditioning on the user prompt question and an input egocentric image that captures user's environment. Notably, existing egocentric datasets lack the detailed annotations that describe the execution of actions. Additionally, the diffusion-based image manipulation models fail to control the state change of an action within the corresponding egocentric image pixel space. To this end, we finetune a visual large language model (VLLM) via visual instruction tuning for curating the enriched action descriptions to address our proposed problem. Moreover, we propose to Learn EGOcentric (LEGO) action frame generation using image and text embeddings from VLLM as additional conditioning. We validate our proposed model on two egocentric datasets -- Ego4D and Epic-Kitchens. Our experiments show prominent improvement over prior image manipulation models in both quantitative and qualitative evaluation. We also conduct detailed ablation studies and analysis to provide insights on our method.
Authors: Kira Prabhu, Jane Wu, Lynn Tsai, Peter Hedman, Dan B Goldman, Ben Poole, Michael Broxton
This paper presents a novel approach to inpainting 3D regions of a scene, given masked multi-view images, by distilling a 2D diffusion model into a learned 3D scene representation (e.g. a NeRF). Unlike 3D generative methods that explicitly condition the diffusion model on camera pose or multi-view information, our diffusion model is conditioned only on a single masked 2D image. Nevertheless, we show that this 2D diffusion model can still serve as a generative prior in a 3D multi-view reconstruction problem where we optimize a NeRF using a combination of score distillation sampling and NeRF reconstruction losses. Predicted depth is used as additional supervision to encourage accurate geometry. We compare our approach to 3D inpainting methods that focus on object removal. Because our method can generate content to fill any 3D masked region, we additionally demonstrate 3D object completion, 3D object replacement, and 3D scene completion.
Authors: Hong-Xing Yu, Haoyi Duan, Junhwa Hur, Kyle Sargent, Michael Rubinstein, William T. Freeman, Forrester Cole, Deqing Sun, Noah Snavely, Jiajun Wu, Charles Herrmann
We introduce WonderJourney, a modularized framework for perpetual 3D scene generation. Unlike prior work on view generation that focuses on a single type of scenes, we start at any user-provided location (by a text description or an image) and generate a journey through a long sequence of diverse yet coherently connected 3D scenes. We leverage an LLM to generate textual descriptions of the scenes in this journey, a text-driven point cloud generation pipeline to make a compelling and coherent sequence of 3D scenes, and a large VLM to verify the generated scenes. We show compelling, diverse visual results across various scene types and styles, forming imaginary "wonderjourneys". Project website: https://kovenyu.com/WonderJourney/
Authors: Jiaman Li, Alexander Clegg, Roozbeh Mottaghi, Jiajun Wu, Xavier Puig, C. Karen Liu
Synthesizing semantic-aware, long-horizon, human-object interaction is critical to simulate realistic human behaviors. In this work, we address the challenging problem of generating synchronized object motion and human motion guided by language descriptions in 3D scenes. We propose Controllable Human-Object Interaction Synthesis (CHOIS), an approach that generates object motion and human motion simultaneously using a conditional diffusion model given a language description, initial object and human states, and sparse object waypoints. While language descriptions inform style and intent, waypoints ground the motion in the scene and can be effectively extracted using high-level planning methods. Naively applying a diffusion model fails to predict object motion aligned with the input waypoints and cannot ensure the realism of interactions that require precise hand-object contact and appropriate contact grounded by the floor. To overcome these problems, we introduce an object geometry loss as additional supervision to improve the matching between generated object motion and input object waypoints. In addition, we design guidance terms to enforce contact constraints during the sampling process of the trained diffusion model.
Authors: Syed Hammad Ahmed, Shengnan Hu, Gita Sukthankar
Natural language supervision has been shown to be effective for zero-shot learning in many computer vision tasks, such as object detection and activity recognition. However, generating informative prompts can be challenging for more subtle tasks, such as video content moderation. This can be difficult, as there are many reasons why a video might be inappropriate, beyond violence and obscenity. For example, scammers may attempt to create junk content that is similar to popular educational videos but with no meaningful information. This paper evaluates the performance of several CLIP variations for content moderation of children's cartoons in both the supervised and zero-shot setting. We show that our proposed model (Vanilla CLIP with Projection Layer) outperforms previous work conducted on the Malicious or Benign (MOB) benchmark for video content moderation. This paper presents an in depth analysis of how context-specific language prompts affect content moderation performance. Our results indicate that it is important to include more context in content moderation prompts, particularly for cartoon videos as they are not well represented in the CLIP training data.
Authors: Emanuel Kuhn
Automated floor plan generation has recently gained momentum with several methods that have been proposed. The CVAAD Floor Plan Auto-Completion workshop challenge introduced MSD, a new dataset that includes existing structural walls of the building as an additional input constraint. This technical report presents an approach for extending a recent work, HouseDiffusion (arXiv:2211.13287 [cs.CV]), to the MSD dataset. The adaption involves modifying the model's transformer layers to condition on a set of wall lines. The report introduces a pre-processing pipeline to extract wall lines from the binary mask of the building structure provided as input. Additionally, it was found that a data processing procedure that simplifies all room polygons to rectangles leads to better performance. This indicates that future work should explore better representations of variable-length polygons in diffusion models. The code will be made available at a later date.
Authors: Risab Biswas, Swalpa Kumar Roy, Umapada Pal
Document image enhancement is a fundamental and important stage for attaining the best performance in any document analysis assignment because there are many degradation situations that could harm document images, making it more difficult to recognize and analyze them. In this paper, we propose \textbf{T2T-BinFormer} which is a novel document binarization encoder-decoder architecture based on a Tokens-to-token vision transformer. Each image is divided into a set of tokens with a defined length using the ViT model, which is then applied several times to model the global relationship between the tokens. However, the conventional tokenization of input data does not adequately reflect the crucial local structure between adjacent pixels of the input image, which results in low efficiency. Instead of using a simple ViT and hard splitting of images for the document image enhancement task, we employed a progressive tokenization technique to capture this local information from an image to achieve more effective results. Experiments on various DIBCO and H-DIBCO benchmarks demonstrate that the proposed model outperforms the existing CNN and ViT-based state-of-the-art methods. In this research, the primary area of examination is the application of the proposed architecture to the task of document binarization. The source code will be made available at https://github.com/RisabBiswas/T2T-BinFormer.
Authors: Shibin Wu, Bang Yang, Zhiyu Ye, Haoqian Wang, Hairong Zheng, Tong Zhang
Medical report generation demands automatic creation of coherent and precise descriptions for medical images. However, the scarcity of labelled medical image-report pairs poses formidable challenges in developing large-scale neural networks capable of harnessing the potential of artificial intelligence, exemplified by large language models. This study builds upon the state-of-the-art vision-language pre-training and fine-tuning approach, BLIP-2, to customize general large-scale foundation models. Integrating adapter tuning and a medical knowledge enhancement loss, our model significantly improves accuracy and coherence. Validation on the dataset of ImageCLEFmedical 2023 demonstrates our model's prowess, achieving the best-averaged results against several state-of-the-art methods. Significant improvements in ROUGE and CIDEr underscore our method's efficacy, highlighting promising outcomes for the rapid medical-domain adaptation of the vision-language foundation models in addressing challenges posed by data scarcity.
Authors: Sloke Shrestha, Sundar Sripada V. S., Asvin Venkataramanan
This project report summarizes our journey to perform stable diffusion fine-tuning on a dataset containing Calvin and Hobbes comics. The purpose is to convert any given input image into the comic style of Calvin and Hobbes, essentially performing style transfer. We train stable-diffusion-v1.5 using Low Rank Adaptation (LoRA) to efficiently speed up the fine-tuning process. The diffusion itself is handled by a Variational Autoencoder (VAE), which is a U-net. Our results were visually appealing for the amount of training time and the quality of input data that went into training.
Authors: Boyang Deng, Yuzhen Lu
Generative models have increasingly impacted relative tasks ranging from image revision and object detection in computer vision to interior design and idea illustration in more general fields. Stable diffusion is an outstanding model series that paves the way for producing high-resolution images with thorough details from text prompts or reference images. It will be an interesting topic about how to leverage the capability of stable diffusion to elevate the image variations of certain categories (e.g., vehicles, humans, and daily objects); particularly, it has the potential to gain improvements for small datasets with image-sparse categories. This study utilized seven categories in the popular COCO dataset and three widespread weed species in Michigan to evaluate the efficiency of a recent version of stable diffusion. In detail, Stable diffusion was used to generate synthetic images belonging to these classes; then, YOLOv8 models were trained based on these synthetic images, whose performance was compared to the models trained on original images. In addition, several techniques (e.g., Image-to-image translation, Dreambooth, ControlNet) of Stable diffusion were leveraged for image generation with different focuses. In spite of the overall results being disappointing, promising results have been achieved in some classes, illustrating the potential of stable diffusion models to improve the performance of detection models, which represent more helpful information being conveyed into the models by the generated images. This seminal study may expedite the adaption of stable diffusion models to classification and detection tasks in different fields.
Authors: Vimal Thilak, Chen Huang, Omid Saremi, Laurent Dinh, Hanlin Goh, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin
Joint embedding (JE) architectures have emerged as a promising avenue for acquiring transferable data representations. A key obstacle to using JE methods, however, is the inherent challenge of evaluating learned representations without access to a downstream task, and an annotated dataset. Without efficient and reliable evaluation, it is difficult to iterate on architectural and training choices for JE methods. In this paper, we introduce LiDAR (Linear Discriminant Analysis Rank), a metric designed to measure the quality of representations within JE architectures. Our metric addresses several shortcomings of recent approaches based on feature covariance rank by discriminating between informative and uninformative features. In essence, LiDAR quantifies the rank of the Linear Discriminant Analysis (LDA) matrix associated with the surrogate SSL task -- a measure that intuitively captures the information content as it pertains to solving the SSL task. We empirically demonstrate that LiDAR significantly surpasses naive rank based approaches in its predictive power of optimal hyperparameters. Our proposed criterion presents a more robust and intuitive means of assessing the quality of representations within JE architectures, which we hope facilitates broader adoption of these powerful techniques in various domains.
Authors: Youngwan Lee, Kwanyong Park, Yoorhim Cho, Yong-Ju Lee, Sung Ju Hwang
Stable diffusion is the mainstay of the text-to-image (T2I) synthesis in the community due to its generation performance and open-source nature. Recently, Stable Diffusion XL (SDXL), the successor of stable diffusion, has received a lot of attention due to its significant performance improvements with a higher resolution of 1024x1024 and a larger model. However, its increased computation cost and model size require higher-end hardware(e.g., bigger VRAM GPU) for end-users, incurring higher costs of operation. To address this problem, in this work, we propose an efficient latent diffusion model for text-to-image synthesis obtained by distilling the knowledge of SDXL. To this end, we first perform an in-depth analysis of the denoising U-Net in SDXL, which is the main bottleneck of the model, and then design a more efficient U-Net based on the analysis. Secondly, we explore how to effectively distill the generation capability of SDXL into an efficient U-Net and eventually identify four essential factors, the core of which is that self-attention is the most important part. With our efficient U-Net and self-attention-based knowledge distillation strategy, we build our efficient T2I models, called KOALA-1B & -700M, while reducing the model size up to 54% and 69% of the original SDXL model. In particular, the KOALA-700M is more than twice as fast as SDXL while still retaining a decent generation quality. We hope that due to its balanced speed-performance tradeoff, our KOALA models can serve as a cost-effective alternative to SDXL in resource-constrained environments.
Authors: Kairui Yang, Zihao Guo, Gengjie Lin, Haotian Dong, Die Zuo, Jibin Peng, Zhao Huang, Zhecheng Xu, Fupeng Li, Ziyun Bai, Di Lin
We advocate the idea of the natural-language-driven(NLD) simulation to efficiently produce the object interactions between multiple objects in the virtual road scenes, for teaching and testing the autonomous driving systems that should take quick action to avoid collision with obstacles with unpredictable motions. The NLD simulation allows the brief natural-language description to control the object interactions, significantly reducing the human efforts for creating a large amount of interaction data. To facilitate the research of NLD simulation, we collect the Language-to-Interaction(L2I) benchmark dataset with 120,000 natural-language descriptions of object interactions in 6 common types of road topologies. Each description is associated with the programming code, which the graphic render can use to visually reconstruct the object interactions in the virtual scenes. As a methodology contribution, we design SimCopilot to translate the interaction descriptions to the renderable code. We use the L2I dataset to evaluate SimCopilot's abilities to control the object motions, generate complex interactions, and generalize interactions across road topologies. The L2I dataset and the evaluation results motivate the relevant research of the NLD simulation.
Authors: Ardian Umam, Cheng-Kun Yang, Min-Hung Chen, Jen-Hui Chuang, Yen-Yu Lin
This paper proposes a cross-modal distillation framework, PartDistill, which transfers 2D knowledge from vision-language models (VLMs) to facilitate 3D shape part segmentation. PartDistill addresses three major challenges in this task: the lack of 3D segmentation in invisible or undetected regions in the 2D projections, inaccurate and inconsistent 2D predictions by VLMs, and the lack of knowledge accumulation across different 3D shapes. PartDistill consists of a teacher network that uses a VLM to make 2D predictions and a student network that learns from the 2D predictions while extracting geometrical features from multiple 3D shapes to carry out 3D part segmentation. A bi-directional distillation, including forward and backward distillations, is carried out within the framework, where the former forward distills the 2D predictions to the student network, and the latter improves the quality of the 2D predictions, which subsequently enhances the final 3D part segmentation. Moreover, PartDistill can exploit generative models that facilitate effortless 3D shape creation for generating knowledge sources to be distilled. Through extensive experiments, PartDistill boosts the existing methods with substantial margins on widely used ShapeNetPart and PartE datasets, by more than 15% and 12% higher mIoU scores, respectively.
Authors: Shashank Kotyan, Ueda Tatsuya, Danilo Vasconcellos Vargas
Most examinations of neural networks' learned latent spaces typically employ dimensionality reduction techniques such as t-SNE or UMAP. While these methods effectively capture the overall sample distribution in the entire learned latent space, they tend to distort the structure of sample distributions within specific classes in the subset of the latent space. This distortion complicates the task of easily distinguishing classes identifiable by neural networks. In response to this challenge, we introduce the k* Distribution methodology. This approach focuses on capturing the characteristics and structure of sample distributions for individual classes within the subset of the learned latent space using local neighborhood analysis. The key concept is to facilitate easy comparison of different k* distributions, enabling analysis of how various classes are processed by the same neural network. This provides a more profound understanding of existing contemporary visualizations. Our study reveals three distinct distributions of samples within the learned latent space subset: a) Fractured, b) Overlapped, and c) Clustered. We note and demonstrate that the distribution of samples within the network's learned latent space significantly varies depending on the class. Furthermore, we illustrate that our analysis can be applied to explore the latent space of diverse neural network architectures, various layers within neural networks, transformations applied to input samples, and the distribution of training and testing data for neural networks. We anticipate that our approach will facilitate more targeted investigations into neural networks by collectively examining the distribution of different samples within the learned latent space.
Authors: Mingwu Zheng, Haiyu Zhang, Hongyu Yang, Liming Chen, Di Huang
Accurate representations of 3D faces are of paramount importance in various computer vision and graphics applications. However, the challenges persist due to the limitations imposed by data discretization and model linearity, which hinder the precise capture of identity and expression clues in current studies. This paper presents a novel 3D morphable face model, named ImFace++, to learn a sophisticated and continuous space with implicit neural representations. ImFace++ first constructs two explicitly disentangled deformation fields to model complex shapes associated with identities and expressions, respectively, which simultaneously facilitate the automatic learning of correspondences across diverse facial shapes. To capture more sophisticated facial details, a refinement displacement field within the template space is further incorporated, enabling a fine-grained learning of individual-specific facial details. Furthermore, a Neural Blend-Field is designed to reinforce the representation capabilities through adaptive blending of an array of local fields. In addition to ImFace++, we have devised an improved learning strategy to extend expression embeddings, allowing for a broader range of expression variations. Comprehensive qualitative and quantitative evaluations demonstrate that ImFace++ significantly advances the state-of-the-art in terms of both face reconstruction fidelity and correspondence accuracy.
Authors: Zhenduo Zhang
Face clustering tasks can learn hierarchical semantic information from large-scale data, which has the potential to help facilitate face recognition. However, there are few works on this problem. This paper explores it by proposing a joint optimization task of label classification and supervised contrastive clustering to introduce the cluster knowledge to the traditional face recognition task in two ways. We first extend ArcFace with a cluster-guided angular margin to adjust the within-class feature distribution according to the hard level of face clustering. Secondly, we propose a supervised contrastive clustering approach to pull the features to the cluster center and propose the cluster-aligning procedure to align the cluster center and the learnable class center in the classifier for joint training. Finally, extensive qualitative and quantitative experiments on popular facial benchmarks demonstrate the effectiveness of our paradigm and its superiority over the existing approaches to face recognition.
Authors: Weilin Wan, Yiming Huang, Shutong Wu, Taku Komura, Wenping Wang, Dinesh Jayaraman, Lingjie Liu
In this study, we introduce a learning-based method for generating high-quality human motion sequences from text descriptions (e.g., ``A person walks forward"). Existing techniques struggle with motion diversity and smooth transitions in generating arbitrary-length motion sequences, due to limited text-to-motion datasets and the pose representations used that often lack expressiveness or compactness. To address these issues, we propose the first method for text-conditioned human motion generation in the frequency domain of motions. We develop a network encoder that converts the motion space into a compact yet expressive parameterized phase space with high-frequency details encoded, capturing the local periodicity of motions in time and space with high accuracy. We also introduce a conditional diffusion model for predicting periodic motion parameters based on text descriptions and a start pose, efficiently achieving smooth transitions between motion sequences associated with different text descriptions. Experiments demonstrate that our approach outperforms current methods in generating a broader variety of high-quality motions, and synthesizing long sequences with natural transitions.
Authors: Hmrishav Bandyopadhyay, Subhadeep Koley, Ayan Das, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Ayan Kumar Bhunia, Yi-Zhe Song
In this paper, we democratise 3D content creation, enabling precise generation of 3D shapes from abstract sketches while overcoming limitations tied to drawing skills. We introduce a novel part-level modelling and alignment framework that facilitates abstraction modelling and cross-modal correspondence. Leveraging the same part-level decoder, our approach seamlessly extends to sketch modelling by establishing correspondence between CLIPasso edgemaps and projected 3D part regions, eliminating the need for a dataset pairing human sketches and 3D shapes. Additionally, our method introduces a seamless in-position editing process as a byproduct of cross-modal part-aligned modelling. Operating in a low-dimensional implicit space, our approach significantly reduces computational demands and processing time.
Authors: Qiuxiao Chen, Xiaojun Qi
Retrieving spatial information and understanding the semantic information of the surroundings are important for Bird's-Eye-View (BEV) semantic segmentation. In the application of autonomous driving, autonomous vehicles need to be aware of their surroundings to drive safely. However, current BEV semantic segmentation techniques, deep Convolutional Neural Networks (CNNs) and transformers, have difficulties in obtaining the global semantic relationships of the surroundings at the early layers of the network. In this paper, we propose to incorporate a novel Residual Graph Convolutional (RGC) module in deep CNNs to acquire both the global information and the region-level semantic relationship in the multi-view image domain. Specifically, the RGC module employs a non-overlapping graph space projection to efficiently project the complete BEV information into graph space. It then builds interconnected spatial and channel graphs to extract spatial information between each node and channel information within each node (i.e., extract contextual relationships of the global features). Furthermore, it uses a downsample residual process to enhance the coordinate feature reuse to maintain the global information. The segmentation data augmentation and alignment module helps to simultaneously augment and align BEV features and ground truth to geometrically preserve their alignment to achieve better segmentation results. Our experimental results on the nuScenes benchmark dataset demonstrate that the RGC network outperforms four state-of-the-art networks and its four variants in terms of IoU and mIoU. The proposed RGC network achieves a higher mIoU of 3.1% than the best state-of-the-art network, BEVFusion. Code and models will be released.
Authors: Junsheng Zhou, Baorui Ma, Wenyuan Zhang, Yi Fang, Yu-Shen Liu, Zhizhong Han
Cross-modality registration between 2D images from cameras and 3D point clouds from LiDARs is a crucial task in computer vision and robotic. Previous methods estimate 2D-3D correspondences by matching point and pixel patterns learned by neural networks, and use Perspective-n-Points (PnP) to estimate rigid transformation during post-processing. However, these methods struggle to map points and pixels to a shared latent space robustly since points and pixels have very different characteristics with patterns learned in different manners (MLP and CNN), and they also fail to construct supervision directly on the transformation since the PnP is non-differentiable, which leads to unstable registration results. To address these problems, we propose to learn a structured cross-modality latent space to represent pixel features and 3D features via a differentiable probabilistic PnP solver. Specifically, we design a triplet network to learn VoxelPoint-to-Pixel matching, where we represent 3D elements using both voxels and points to learn the cross-modality latent space with pixels. We design both the voxel and pixel branch based on CNNs to operate convolutions on voxels/pixels represented in grids, and integrate an additional point branch to regain the information lost during voxelization. We train our framework end-to-end by imposing supervisions directly on the predicted pose distribution with a probabilistic PnP solver. To explore distinctive patterns of cross-modality features, we design a novel loss with adaptive-weighted optimization for cross-modality feature description. The experimental results on KITTI and nuScenes datasets show significant improvements over the state-of-the-art methods. The code and models are available at https://github.com/junshengzhou/VP2P-Match.
Authors: Israt Zarin Era, Imtiaz Ahmed, Zhichao Liu, Srinjoy Das
Foundation models are currently driving a paradigm shift in computer vision tasks for various fields including biology, astronomy, and robotics among others, leveraging user-generated prompts to enhance their performance. In the manufacturing domain, accurate image-based defect segmentation is imperative to ensure product quality and facilitate real-time process control. However, such tasks are often characterized by multiple challenges including the absence of labels and the requirement for low latency inference among others. To address these issues, we construct a framework for image segmentation using a state-of-the-art Vision Transformer (ViT) based Foundation model (Segment Anything Model) with a novel multi-point prompt generation scheme using unsupervised clustering. We apply our framework to perform real-time porosity segmentation in a case study of laser base powder bed fusion (L-PBF) and obtain high Dice Similarity Coefficients (DSC) without the necessity for any supervised fine-tuning in the model. Using such lightweight foundation model inference in conjunction with unsupervised prompt generation, we envision the construction of a real-time anomaly detection pipeline that has the potential to revolutionize the current laser-based additive manufacturing processes, thereby facilitating the shift towards Industry 4.0 and promoting defect-free production along with operational efficiency.
Authors: Thomas Westfechtel, Dexuan Zhang, Tatsuya Harada
Unsupervised domain adaptation (UDA) tries to overcome the tedious work of labeling data by leveraging a labeled source dataset and transferring its knowledge to a similar but different target dataset. On the other hand, current vision-language models exhibit astonishing zero-shot prediction capabilities. In this work, we combine knowledge gained through UDA with the inherent knowledge of vision-language models. In a first step, we generate the zero-shot predictions of the source and target dataset using the vision-language model. Since zero-shot predictions usually exhibit a large entropy, meaning that the class probabilities are rather evenly distributed, we first adjust the distribution to accentuate the winning probabilities. This is done using both source and target data to keep the relative confidence between source and target data. We then employ a conventional DA method, to gain the knowledge from the source dataset, in combination with self-knowledge distillation, to maintain the inherent knowledge of the vision-language model. We further combine our method with a gradual source domain expansion strategy (GSDE) and show that this strategy can also benefit by including zero-shot predictions. We conduct experiments and ablation studies on three benchmarks (OfficeHome, VisDA, and DomainNet) and outperform state-of-the-art methods. We further show in ablation studies the contributions of different parts of our algorithm.
Authors: Zhaoheng Zheng, Jingmin Wei, Xuefeng Hu, Haidong Zhu, Ram Nevatia
Low-shot image classification, where training images are limited or inaccessible, has benefited from recent progress on pre-trained vision-language (VL) models with strong generalizability, e.g. CLIP. Prompt learning methods built with VL models generate text features from the class names that only have confined class-specific information. Large Language Models (LLMs), with their vast encyclopedic knowledge, emerge as the complement. Thus, in this paper, we discuss the integration of LLMs to enhance pre-trained VL models, specifically on low-shot classification. However, the domain gap between language and vision blocks the direct application of LLMs. Thus, we propose LLaMP, Large Language Models as Prompt learners, that produces adaptive prompts for the CLIP text encoder, establishing it as the connecting bridge. Experiments show that, compared with other state-of-the-art prompt learning methods, LLaMP yields better performance on both zero-shot generalization and few-shot image classification, over a spectrum of 11 datasets.
Authors: Gyeongrok Oh, Jaehwan Jeong, Sieun Kim, Wonmin Byeon, Jinkyu Kim, Sungwoong Kim, Hyeokmin Kwon, Sangpil Kim
Recently, video generation has attracted massive attention and yielded noticeable outcomes. Concerning the characteristics of video, multi-text conditioning incorporating sequential events is necessary for next-step video generation. In this work, we propose a novel multi-text video generation~(MTVG) by directly utilizing a pre-trained diffusion-based text-to-video~(T2V) generation model without additional fine-tuning. To generate consecutive video segments, visual consistency generated by distinct prompts is necessary with diverse variations, such as motion and content-related transitions. Our proposed MTVG includes Dynamic Noise and Last Frame Aware Inversion which reinitialize the noise latent to preserve visual coherence between videos of different prompts and prevent repetitive motion or contents. Furthermore, we present Structure Guiding Sampling to maintain the global appearance across the frames in a single video clip, where we leverage iterative latent updates across the preceding frame. Additionally, our Prompt Generator allows for arbitrary format of text conditions consisting of diverse events. As a result, our extensive experiments, including diverse transitions of descriptions, demonstrate that our proposed methods show superior generated outputs in terms of semantically coherent and temporally seamless video.Video examples are available in our project page: https://kuai-lab.github.io/mtvg-page.
Authors: Zongjie Li, Chaozheng Wang, Chaowei Liu, Pingchuan Ma, Daoyuan Wu, Shuai Wang, Cuiyun Gao
With recent advancements in Large Multimodal Models (LMMs) across various domains, a novel prompting method called visual referring prompting has emerged, showing significant potential in enhancing human-computer interaction within multimodal systems. This method offers a more natural and flexible approach to human interaction with these systems compared to traditional text descriptions or coordinates. However, the categorization of visual referring prompting remains undefined, and its impact on the performance of LMMs has yet to be formally examined. In this study, we conduct the first comprehensive analysis of LMMs using a variety of visual referring prompting strategies. We introduce a benchmark dataset called VRPTEST, comprising 3 different visual tasks and 2,275 images, spanning diverse combinations of prompt strategies. Using VRPTEST, we conduct a comprehensive evaluation of eight versions of prominent open-source and proprietary foundation models, including two early versions of GPT-4V. We develop an automated assessment framework based on software metamorphic testing techniques to evaluate the accuracy of LMMs without the need for human intervention or manual labeling. We find that the current proprietary models generally outperform the open-source ones, showing an average accuracy improvement of 22.70%; however, there is still potential for improvement. Moreover, our quantitative analysis shows that the choice of prompt strategy significantly affects the accuracy of LMMs, with variations ranging from -17.5% to +7.3%. Further case studies indicate that an appropriate visual referring prompting strategy can improve LMMs' understanding of context and location information, while an unsuitable one might lead to answer rejection. We also provide insights on minimizing the negative impact of visual referring prompting on LMMs.
Authors: Yong Liu, Sule Bai, Guanbin Li, Yitong Wang, Yansong Tang
This paper studies open-vocabulary segmentation (OVS) through calibrating in-vocabulary and domain-biased embedding space with generalized contextual prior of CLIP. As the core of open-vocabulary understanding, alignment of visual content with the semantics of unbounded text has become the bottleneck of this field. To address this challenge, recent works propose to utilize CLIP as an additional classifier and aggregate model predictions with CLIP classification results. Despite their remarkable progress, performance of OVS methods in relevant scenarios is still unsatisfactory compared with supervised counterparts. We attribute this to the in-vocabulary embedding and domain-biased CLIP prediction. To this end, we present a Semantic-assisted CAlibration Network (SCAN). In SCAN, we incorporate generalized semantic prior of CLIP into proposal embedding to avoid collapsing on known categories. Besides, a contextual shift strategy is applied to mitigate the lack of global context and unnatural background noise. With above designs, SCAN achieves state-of-the-art performance on all popular open-vocabulary segmentation benchmarks. Furthermore, we also focus on the problem of existing evaluation system that ignores semantic duplication across categories, and propose a new metric called Semantic-Guided IoU (SG-IoU).
Authors: Tuan Hoang, Santu Rana, Sunil Gupta, Svetha Venkatesh
Recent data-privacy laws have sparked interest in machine unlearning, which involves removing the effect of specific training samples from a learnt model as if they were never present in the original training dataset. The challenge of machine unlearning is to discard information about the ``forget'' data in the learnt model without altering the knowledge about the remaining dataset and to do so more efficiently than the naive retraining approach. To achieve this, we adopt a projected-gradient based learning method, named as Projected-Gradient Unlearning (PGU), in which the model takes steps in the orthogonal direction to the gradient subspaces deemed unimportant for the retaining dataset, so as to its knowledge is preserved. By utilizing Stochastic Gradient Descent (SGD) to update the model weights, our method can efficiently scale to any model and dataset size. We provide empirically evidence to demonstrate that our unlearning method can produce models that behave similar to models retrained from scratch across various metrics even when the training dataset is no longer accessible. Our code is available at https://github.com/hnanhtuan/projected_gradient_unlearning.
Authors: Jiayi Kong, Baixin Xu, Xurui Song, Chen Qian, Jun Luo, Ying He
Neural radiance fields (NeRF) typically require a complete set of images taken from multiple camera perspectives to accurately reconstruct geometric details. However, this approach raise significant privacy concerns in the context of facial reconstruction. The critical need for privacy protection often leads invidividuals to be reluctant in sharing their facial images, due to fears of potential misuse or security risks. Addressing these concerns, we propose a method that leverages privacy-preserving images for reconstructing 3D head geometry within the NeRF framework. Our method stands apart from traditional facial reconstruction techniques as it does not depend on RGB information from images containing sensitive facial data. Instead, it effectively generates plausible facial geometry using a series of identity-obscured inputs, thereby protecting facial privacy.
Authors: Zijian Shen, Zhenping Mu, Xiangxiang Li
The increasing accident rate brought about by the explosive growth of automobiles has made the research on active safety systems of automobiles increasingly important. The importance of improving the accuracy of vehicle target detection is self-evident. To achieve the goals of vehicle detection and distance estimation and provide safety warnings, a Distance Estimation Safety Warning System (DESWS) based on a new neural network model (YOLOv5s-SE) by replacing the IoU with DIoU, embedding SE attention module, and a distance estimation method through using the principle of similar triangles was proposed. In addition, a method that can give safety suggestions based on the estimated distance using nonparametric testing was presented in this work. Through the simulation experiment, it was verified that the mAP was improved by 5.5% and the purpose of giving safety suggestions based on the estimated distance information can be achieved.
Authors: Yunhan Zhao, Haoyu Ma, Shu Kong, Charless Fowlkes
Egocentric sensors such as AR/VR devices capture human-object interactions and offer the potential to provide task-assistance by recalling 3D locations of objects of interest in the surrounding environment. This capability requires instance tracking in real-world 3D scenes from egocentric videos (IT3DEgo). We explore this problem by first introducing a new benchmark dataset, consisting of RGB and depth videos, per-frame camera pose, and instance-level annotations in both 2D camera and 3D world coordinates. We present an evaluation protocol which evaluates tracking performance in 3D coordinates with two settings for enrolling instances to track: (1) single-view online enrollment where an instance is specified on-the-fly based on the human wearer's interactions. and (2) multi-view pre-enrollment where images of an instance to be tracked are stored in memory ahead of time. To address IT3DEgo, we first re-purpose methods from relevant areas, e.g., single object tracking (SOT) -- running SOT methods to track instances in 2D frames and lifting them to 3D using camera pose and depth. We also present a simple method that leverages pretrained segmentation and detection models to generate proposals from RGB frames and match proposals with enrolled instance images. Perhaps surprisingly, our extensive experiments show that our method (with no finetuning) significantly outperforms SOT-based approaches. We conclude by arguing that the problem of egocentric instance tracking is made easier by leveraging camera pose and using a 3D allocentric (world) coordinate representation.
Authors: Timothy Schaumlöffel, Arthur Aubret, Gemma Roig, Jochen Triesch
Infants' ability to recognize and categorize objects develops gradually. The second year of life is marked by both the emergence of more semantic visual representations and a better understanding of word meaning. This suggests that language input may play an important role in shaping visual representations. However, even in suitable contexts for word learning like dyadic play sessions, caregivers utterances are sparse and ambiguous, often referring to objects that are different from the one to which the child attends. Here, we systematically investigate to what extent caregivers' utterances can nevertheless enhance visual representations. For this we propose a computational model of visual representation learning during dyadic play. We introduce a synthetic dataset of ego-centric images perceived by a toddler-agent that moves and rotates toy objects in different parts of its home environment while hearing caregivers' utterances, modeled as captions. We propose to model toddlers' learning as simultaneously aligning representations for 1) close-in-time images and 2) co-occurring images and utterances. We show that utterances with statistics matching those of real caregivers give rise to representations supporting improved category recognition. Our analysis reveals that a small decrease/increase in object-relevant naming frequencies can drastically impact the learned representations. This affects the attention on object names within an utterance, which is required for efficient visuo-linguistic alignment. Overall, our results support the hypothesis that caregivers' naming utterances can improve toddlers' visual representations.
Authors: Guoqing Yang, Zhiming Luo, Jianzhe Gao, Yingxin Lai, Kun Yang, Yifan He, Shaozi Li
Human behavior anomaly detection aims to identify unusual human actions, playing a crucial role in intelligent surveillance and other areas. The current mainstream methods still adopt reconstruction or future frame prediction techniques. However, reconstructing or predicting low-level pixel features easily enables the network to achieve overly strong generalization ability, allowing anomalies to be reconstructed or predicted as effectively as normal data. Different from their methods, inspired by the Student-Teacher Network, we propose a novel framework called the Multilevel Guidance-Exploration Network(MGENet), which detects anomalies through the difference in high-level representation between the Guidance and Exploration network. Specifically, we first utilize the pre-trained Normalizing Flow that takes skeletal keypoints as input to guide an RGB encoder, which takes unmasked RGB frames as input, to explore motion latent features. Then, the RGB encoder guides the mask encoder, which takes masked RGB frames as input, to explore the latent appearance feature. Additionally, we design a Behavior-Scene Matching Module(BSMM) to detect scene-related behavioral anomalies. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on ShanghaiTech and UBnormal datasets, with AUC of 86.9 % and 73.5 %, respectively. The code will be available on https://github.com/molu-ggg/GENet.
Authors: Rasel Ahmed Bhuiyan, Adam Czajka
Post-mortem iris recognition is an emerging application of iris-based human identification in a forensic setup, able to correctly identify deceased subjects even three weeks post-mortem. This technique thus is considered as an important component of future forensic toolkits. The current advancements in this field are seriously slowed down by exceptionally difficult data collection, which can happen in mortuary conditions, at crime scenes, or in ``body farm'' facilities. This paper makes a novel contribution to facilitate progress in post-mortem iris recognition by offering a conditional StyleGAN-based iris synthesis model, trained on the largest-available dataset of post-mortem iris samples acquired from more than 350 subjects, generating -- through appropriate exploration of StyleGAN latent space -- multiple within-class (same identity) and between-class (different new identities) post-mortem iris images, compliant with ISO/IEC 29794-6, and with decomposition deformations controlled by the requested PMI (post mortem interval). Besides an obvious application to enhance the existing, very sparse, post-mortem iris datasets to advance -- among others -- iris presentation attack endeavors, we anticipate it may be useful to generate samples that would expose professional forensic human examiners to never-seen-before deformations for various PMIs, increasing their training effectiveness. The source codes and model weights are made available with the paper.
Authors: Ryota Maeda, Shinsaku Hiura
Polarization is well known for its ability to decompose diffuse and specular reflections. However, the existing decomposition methods only focus on direct reflection and overlook multiple reflections, especially specular inter-reflection. In this paper, we propose a novel decomposition method for handling specular inter-reflection of metal objects by using a unique polarimetric feature: the rotation direction of linear polarization. This rotation direction serves as a discriminative factor between direct and inter-reflection on specular surfaces. To decompose the reflectance components, we actively rotate the linear polarization of incident light and analyze the rotation direction of the reflected light. We evaluate our method using both synthetic and real data, demonstrating its effectiveness in decomposing specular inter-reflections of metal objects. Furthermore, we demonstrate that our method can be combined with other decomposition methods for a detailed analysis of light transport. As a practical application, we show its effectiveness in improving the accuracy of 3D measurement against strong specular inter-reflection.
Authors: Tiantian Wang, Xinxin Zuo, Fangzhou Mu, Jian Wang, Ming-Hsuan Yang
We present a first step towards 4D (3D and time) human video stylization, which addresses style transfer, novel view synthesis and human animation within a unified framework. While numerous video stylization methods have been developed, they are often restricted to rendering images in specific viewpoints of the input video, lacking the capability to generalize to novel views and novel poses in dynamic scenes. To overcome these limitations, we leverage Neural Radiance Fields (NeRFs) to represent videos, conducting stylization in the rendered feature space. Our innovative approach involves the simultaneous representation of both the human subject and the surrounding scene using two NeRFs. This dual representation facilitates the animation of human subjects across various poses and novel viewpoints. Specifically, we introduce a novel geometry-guided tri-plane representation, significantly enhancing feature representation robustness compared to direct tri-plane optimization. Following the video reconstruction, stylization is performed within the NeRFs' rendered feature space. Extensive experiments demonstrate that the proposed method strikes a superior balance between stylized textures and temporal coherence, surpassing existing approaches. Furthermore, our framework uniquely extends its capabilities to accommodate novel poses and viewpoints, making it a versatile tool for creative human video stylization.
Authors: Nir Zabari, Aharon Azulay, Alexey Gorkor, Tavi Halperin, Ohad Fried
The colorization of grayscale images is a complex and subjective task with significant challenges. Despite recent progress in employing large-scale datasets with deep neural networks, difficulties with controllability and visual quality persist. To tackle these issues, we present a novel image colorization framework that utilizes image diffusion techniques with granular text prompts. This integration not only produces colorization outputs that are semantically appropriate but also greatly improves the level of control users have over the colorization process. Our method provides a balance between automation and control, outperforming existing techniques in terms of visual quality and semantic coherence. We leverage a pretrained generative Diffusion Model, and show that we can finetune it for the colorization task without losing its generative power or attention to text prompts. Moreover, we present a novel CLIP-based ranking model that evaluates color vividness, enabling automatic selection of the most suitable level of vividness based on the specific scene semantics. Our approach holds potential particularly for color enhancement and historical image colorization.
Authors: Fei Wang, Dan Guo, Kun Li, Meng Wang
Video Motion Magnification (VMM) aims to break the resolution limit of human visual perception capability and reveal the imperceptible minor motion that contains valuable information in the macroscopic domain. However, challenges arise in this task due to photon noise inevitably introduced by photographic devices and spatial inconsistency in amplification, leading to flickering artifacts in static fields and motion blur and distortion in dynamic fields in the video. Existing methods focus on explicit motion modeling without emphasizing prioritized denoising during the motion magnification process. This paper proposes a novel dynamic filtering strategy to achieve static-dynamic field adaptive denoising. Specifically, based on Eulerian theory, we separate texture and shape to extract motion representation through inter-frame shape differences, expecting to leverage these subdivided features to solve this task finely. Then, we introduce a novel dynamic filter that eliminates noise cues and preserves critical features in the motion magnification and amplification generation phases. Overall, our unified framework, EulerMormer, is a pioneering effort to first equip with Transformer in learning-based VMM. The core of the dynamic filter lies in a global dynamic sparse cross-covariance attention mechanism that explicitly removes noise while preserving vital information, coupled with a multi-scale dual-path gating mechanism that selectively regulates the dependence on different frequency features to reduce spatial attenuation and complement motion boundaries. We demonstrate extensive experiments that EulerMormer achieves more robust video motion magnification from the Eulerian perspective, significantly outperforming state-of-the-art methods. The source code is available at https://github.com/VUT-HFUT/EulerMormer.
Authors: Xuelin Zhu, Jiuxin Cao, Jian liu, Dongqi Tang, Furong Xu, Weijia Liu, Jiawei Ge, Bo Liu, Qingpei Guo, Tianyi Zhang
Pre-trained vision-language models have notably accelerated progress of open-world concept recognition. Their impressive zero-shot ability has recently been transferred to multi-label image classification via prompt tuning, enabling to discover novel labels in an open-vocabulary manner. However, this paradigm suffers from non-trivial training costs, and becomes computationally prohibitive for a large number of candidate labels. To address this issue, we note that vision-language pre-training aligns images and texts in a unified embedding space, making it potential for an adapter network to identify labels in visual modality while be trained in text modality. To enhance such cross-modal transfer ability, a simple yet effective method termed random perturbation is proposed, which enables the adapter to search for potential visual embeddings by perturbing text embeddings with noise during training, resulting in better performance in visual modality. Furthermore, we introduce an effective approach to employ large language models for multi-label instruction-following text generation. In this way, a fully automated pipeline for visual label recognition is developed without relying on any manual data. Extensive experiments on public benchmarks show the superiority of our method in various multi-label classification tasks.
Authors: Jiawei Fan, Chao Li, Xiaolong Liu, Meina Song, Anbang Yao
In recent years, knowledge distillation methods based on contrastive learning have achieved promising results on image classification and object detection tasks. However, in this line of research, we note that less attention is paid to semantic segmentation. Existing methods heavily rely on data augmentation and memory buffer, which entail high computational resource demands when applying them to handle semantic segmentation that requires to preserve high-resolution feature maps for making dense pixel-wise predictions. In order to address this problem, we present Augmentation-free Dense Contrastive Knowledge Distillation (Af-DCD), a new contrastive distillation learning paradigm to train compact and accurate deep neural networks for semantic segmentation applications. Af-DCD leverages a masked feature mimicking strategy, and formulates a novel contrastive learning loss via taking advantage of tactful feature partitions across both channel and spatial dimensions, allowing to effectively transfer dense and structured local knowledge learnt by the teacher model to a target student model while maintaining training efficiency. Extensive experiments on five mainstream benchmarks with various teacher-student network pairs demonstrate the effectiveness of our approach. For instance, the DeepLabV3-Res18|DeepLabV3-MBV2 model trained by Af-DCD reaches 77.03%|76.38% mIOU on Cityscapes dataset when choosing DeepLabV3-Res101 as the teacher, setting new performance records. Besides that, Af-DCD achieves an absolute mIOU improvement of 3.26%|3.04%|2.75%|2.30%|1.42% compared with individually trained counterpart on Cityscapes|Pascal VOC|Camvid|ADE20K|COCO-Stuff-164K. Code is available at https://github.com/OSVAI/Af-DCD
Authors: Peng Tang, Xintong Yan, Yang Nan, Xiaobin Hu, Xiaobin Hu, Bjoern H Menzee.Sebastian Krammer, Tobias Lasser
Most convolutional neural network (CNN) based methods for skin cancer classification obtain their results using only dermatological images. Although good classification results have been shown, more accurate results can be achieved by considering the patient's metadata, which is valuable clinical information for dermatologists. Current methods only use the simple joint fusion structure (FS) and fusion modules (FMs) for the multi-modal classification methods, there still is room to increase the accuracy by exploring more advanced FS and FM. Therefore, in this paper, we design a new fusion method that combines dermatological images (dermoscopy images or clinical images) and patient metadata for skin cancer classification from the perspectives of FS and FM. First, we propose a joint-individual fusion (JIF) structure that learns the shared features of multi-modality data and preserves specific features simultaneously. Second, we introduce a fusion attention (FA) module that enhances the most relevant image and metadata features based on both the self and mutual attention mechanism to support the decision-making pipeline. We compare the proposed JIF-MMFA method with other state-of-the-art fusion methods on three different public datasets. The results show that our JIF-MMFA method improves the classification results for all tested CNN backbones and performs better than the other fusion methods on the three public datasets, demonstrating our method's effectiveness and robustness
Authors: Ronan Docherty, Isaac Squires, Antonis Vamvakeros, Samuel J. Cooper
Segmentation is the assigning of a semantic class to every pixel in an image and is a prerequisite for various statistical analysis tasks in materials science, like phase quantification, physics simulations or morphological characterization. The wide range of length scales, imaging techniques and materials studied in materials science means any segmentation algorithm must generalise to unseen data and support abstract, user-defined semantic classes. Trainable segmentation is a popular interactive segmentation paradigm where a classifier is trained to map from image features to user drawn labels. SAMBA is a trainable segmentation tool that uses Meta's Segment Anything Model (SAM) for fast, high-quality label suggestions and a random forest classifier for robust, generalizable segmentations. It is accessible in the browser (https://www.sambasegment.com/) without the need to download any external dependencies. The segmentation backend is run in the cloud, so does not require the user to have powerful hardware.
Authors: Manuel Combarro Simón, Pierre Talbot, Grégoire Danoy, Jedrzej Musial, Mohammed Alswaitti, Pascal Bouvry
Satellite imagery solutions are widely used to study and monitor different regions of the Earth. However, a single satellite image can cover only a limited area. In cases where a larger area of interest is studied, several images must be stitched together to create a single larger image, called a mosaic, that can cover the area. Today, with the increasing number of satellite images available for commercial use, selecting the images to build the mosaic is challenging, especially when the user wants to optimize one or more parameters, such as the total cost and the cloud coverage percentage in the mosaic. More precisely, for this problem the input is an area of interest, several satellite images intersecting the area, a list of requirements relative to the image and the mosaic, such as cloud coverage percentage, image resolution, and a list of objectives to optimize. We contribute to the constraint and mixed integer lineal programming formulation of this new problem, which we call the \textit{satellite image mosaic selection problem}, which is a multi-objective extension of the polygon cover problem. We propose a dataset of realistic and challenging instances, where the images were captured by the satellite constellations SPOT, Pl\'eiades and Pl\'eiades Neo. We evaluate and compare the two proposed models and show their efficiency for large instances, up to 200 images.
Authors: Finn Behrendt, Debayan Bhattacharya, Robin Mieling, Lennart Maack, Julia Krüger, Roland Opfer, Alexander Schlaefer
Unsupervised anomaly detection in Brain MRIs aims to identify abnormalities as outliers from a healthy training distribution. Reconstruction-based approaches that use generative models to learn to reconstruct healthy brain anatomy are commonly used for this task. Diffusion models are an emerging class of deep generative models that show great potential regarding reconstruction fidelity. However, they face challenges in preserving intensity characteristics in the reconstructed images, limiting their performance in anomaly detection. To address this challenge, we propose to condition the denoising mechanism of diffusion models with additional information about the image to reconstruct coming from a latent representation of the noise-free input image. This conditioning enables high-fidelity reconstruction of healthy brain structures while aligning local intensity characteristics of input-reconstruction pairs. We evaluate our method's reconstruction quality, domain adaptation features and finally segmentation performance on publicly available data sets with various pathologies. Using our proposed conditioning mechanism we can reduce the false-positive predictions and enable a more precise delineation of anomalies which significantly enhances the anomaly detection performance compared to established state-of-the-art approaches to unsupervised anomaly detection in brain MRI. Furthermore, our approach shows promise in domain adaptation across different MRI acquisitions and simulated contrasts, a crucial property of general anomaly detection methods.
Authors: Shuangmei Wang, Yang Cao, Tieru Wu
Few-shot class-incremental learning (FSCIL) struggles to incrementally recognize novel classes from few examples without catastrophic forgetting of old classes or overfitting to new classes. We propose TLCE, which ensembles multiple pre-trained models to improve separation of novel and old classes. TLCE minimizes interference between old and new classes by mapping old class images to quasi-orthogonal prototypes using episodic training. It then ensembles diverse pre-trained models to better adapt to novel classes despite data imbalance. Extensive experiments on various datasets demonstrate that our transfer learning ensemble approach outperforms state-of-the-art FSCIL methods.
Authors: Mayank Vatsa, Anubhooti Jain, Richa Singh
Recently, transformers have become incredibly popular in computer vision and vision-language tasks. This notable rise in their usage can be primarily attributed to the capabilities offered by attention mechanisms and the outstanding ability of transformers to adapt and apply themselves to a variety of tasks and domains. Their versatility and state-of-the-art performance have established them as indispensable tools for a wide array of applications. However, in the constantly changing landscape of machine learning, the assurance of the trustworthiness of transformers holds utmost importance. This paper conducts a thorough examination of vision-language transformers, employing three fundamental principles of responsible AI: Bias, Robustness, and Interpretability. The primary objective of this paper is to delve into the intricacies and complexities associated with the practical use of transformers, with the overarching goal of advancing our comprehension of how to enhance their reliability and accountability.
Authors: Kang Ge, Chen Wang, Yutao Guo
Large-scale foundation models have become the mainstream method in the field of deep learning, while in civil engineering, the scale of AI models is strictly limited. In this work, vision foundation model is introduced for crack segmentation. Two Parameter-efficient fine-tuning methods, adapter and low-rank adaptation, are adopted to fine-tune the foundation model in the field of semantic segmentation: Segment Anything Model (SAM). The fine-tuned model CrackSAM is much larger than all the existing crack segmentation models, but shows excellent performance. To test the zero-shot performance of the proposed method, two unique datasets related to road and exterior wall cracks are collected, annotated and open-sourced, in total 810 images. Comparative experiments are conducted with twelve mature semantic segmentation models. On datasets with artificial noise and previously unseen datasets, the performance of CrackSAM far exceeds that of all state-of-the-art models. CrackSAM exhibits remarkable superiority, particularly in challenging conditions such as dim lighting, shadows, road markings, construction joints, and other interference factors. Such cross-scenario results demonstrate the outstanding zero-shot capability of foundation models, and provide new ideas for the development of vision models in civil engineering.
Authors: Yiqun Zhang, Zhenyue Qin, Yang Liu, Dylan Campbell
We introduce a pipeline to address anatomical inaccuracies in Stable Diffusion generated hand images. The initial step involves constructing a specialized dataset, focusing on hand anomalies, to train our models effectively. A finetuned detection model is pivotal for precise identification of these anomalies, ensuring targeted correction. Body pose estimation aids in understanding hand orientation and positioning, crucial for accurate anomaly correction. The integration of ControlNet and InstructPix2Pix facilitates sophisticated inpainting and pixel-level transformation, respectively. This dual approach allows for high-fidelity image adjustments. This comprehensive approach ensures the generation of images with anatomically accurate hands, closely resembling real-world appearances. Our experimental results demonstrate the pipeline's efficacy in enhancing hand image realism in Stable Diffusion outputs. We provide an online demo at https://fixhand.yiqun.io
Authors: Xuying Zhang, Bo-Wen Yin, Yuming Chen, Zheng Lin, Yunheng Li, Qibin Hou, Ming-Ming Cheng
Recent progress in the text-driven 3D stylization of a single object has been considerably promoted by CLIP-based methods. However, the stylization of multi-object 3D scenes is still impeded in that the image-text pairs used for pre-training CLIP mostly consist of an object. Meanwhile, the local details of multiple objects may be susceptible to omission due to the existing supervision manner primarily relying on coarse-grained contrast of image-text pairs. To overcome these challenges, we present a novel framework, dubbed TeMO, to parse multi-object 3D scenes and edit their styles under the contrast supervision at multiple levels. We first propose a Decoupled Graph Attention (DGA) module to distinguishably reinforce the features of 3D surface points. Particularly, a cross-modal graph is constructed to align the object points accurately and noun phrases decoupled from the 3D mesh and textual description. Then, we develop a Cross-Grained Contrast (CGC) supervision system, where a fine-grained loss between the words in the textual description and the randomly rendered images are constructed to complement the coarse-grained loss. Extensive experiments show that our method can synthesize high-quality stylized content and outperform the existing methods over a wide range of multi-object 3D meshes. Our code and results will be made publicly available
Authors: Zhixiang Wei, Lin Chen, Yi Jin, Xiaoxiao Ma, Tianle Liu, Pengyang Lin, Ben Wang, Huaian Chen, Jinjin Zheng
In this paper, we first assess and harness various Vision Foundation Models (VFMs) in the context of Domain Generalized Semantic Segmentation (DGSS). Driven by the motivation that Leveraging Stronger pre-trained models and Fewer trainable parameters for Superior generalizability, we introduce a robust fine-tuning approach, namely Rein, to parameter-efficiently harness VFMs for DGSS. Built upon a set of trainable tokens, each linked to distinct instances, Rein precisely refines and forwards the feature maps from each layer to the next layer within the backbone. This process produces diverse refinements for different categories within a single image. With fewer trainable parameters, Rein efficiently fine-tunes VFMs for DGSS tasks, surprisingly surpassing full parameter fine-tuning. Extensive experiments across various settings demonstrate that Rein significantly outperforms state-of-the-art methods. Remarkably, with just an extra 1% of trainable parameters within the frozen backbone, Rein achieves a mIoU of 68.1% on the Cityscapes, without accessing any real urban-scene datasets.
Authors: Dayoung Gong, Joonseok Lee, Deunsol Jung, Suha Kwak, Minsu Cho
Sequence prediction on temporal data requires the ability to understand compositional structures of multi-level semantics beyond individual and contextual properties. The task of temporal action segmentation, which aims at translating an untrimmed activity video into a sequence of action segments, remains challenging for this reason. This paper addresses the problem by introducing an effective activity grammar to guide neural predictions for temporal action segmentation. We propose a novel grammar induction algorithm that extracts a powerful context-free grammar from action sequence data. We also develop an efficient generalized parser that transforms frame-level probability distributions into a reliable sequence of actions according to the induced grammar with recursive rules. Our approach can be combined with any neural network for temporal action segmentation to enhance the sequence prediction and discover its compositional structure. Experimental results demonstrate that our method significantly improves temporal action segmentation in terms of both performance and interpretability on two standard benchmarks, Breakfast and 50 Salads.
Authors: Zheng Lian, Licai Sun, Haiyang Sun, Kang Chen, Zhuofan Wen, Hao Gu, Shun Chen, Bin Liu, Jianhua Tao
Recently, GPT-4 with Vision (GPT-4V) has shown remarkable performance across various multimodal tasks. However, its efficacy in emotion recognition remains a question. This paper quantitatively evaluates GPT-4V's capabilities in multimodal emotion understanding, encompassing tasks such as facial emotion recognition, visual sentiment analysis, micro-expression recognition, dynamic facial emotion recognition, and multimodal emotion recognition. Our experiments show that GPT-4V exhibits impressive multimodal and temporal understanding capabilities, even surpassing supervised systems in some tasks. Despite these achievements, GPT-4V is currently tailored for general domains. It performs poorly in micro-expression recognition that requires specialized expertise. The main purpose of this paper is to present quantitative results of GPT-4V on emotion understanding and establish a zero-shot benchmark for future research. Code and evaluation results are available at: https://github.com/zeroQiaoba/gpt4v-emotion.
Authors: Julius Weißmann, Markus Seidl, Anya Dietrich, Martin Haltrich
Historic scribe identification is a substantial task for obtaining information about the past. Uniform script styles, such as the Carolingian minuscule, make it a difficult task for classification to focus on meaningful features. Therefore, we demonstrate in this paper the importance of cross-codex training data for CNN based text-independent off-line scribe identification, to overcome codex dependent overfitting. We report three main findings: First, we found that preprocessing with masked grayscale images instead of RGB images clearly increased the F1-score of the classification results. Second, we trained different neural networks on our complex data, validating time and accuracy differences in order to define the most reliable network architecture. With AlexNet, the network with the best trade-off between F1-score and time, we achieved for individual classes F1-scores of up to 0,96 on line level and up to 1.0 on page level in classification. Third, we could replicate the finding that the CNN output can be further improved by implementing a reject option, giving more stable results. We present the results on our large scale open source dataset -- the Codex Claustroneoburgensis database (CCl-DB) -- containing a significant number of writings from different scribes in several codices. We demonstrate for the first time on a dataset with such a variety of codices that paleographic decisions can be reproduced automatically and precisely with CNNs. This gives manifold new and fast possibilities for paleographers to gain insights into unlabeled material, but also to develop further hypotheses.
Authors: Yuechen Zhang, Shengju Qian, Bohao Peng, Shu Liu, Jiaya Jia
This study targets a critical aspect of multi-modal LLMs' (LLMs&VLMs) inference: explicit controllable text generation. Multi-modal LLMs empower multi-modality understanding with the capability of semantic generation yet bring less explainability and heavier reliance on prompt contents due to their autoregressive generative nature. While manipulating prompt formats could improve outputs, designing specific and precise prompts per task can be challenging and ineffective. To tackle this issue, we introduce a novel inference method, Prompt Highlighter, which enables users to highlight specific prompt spans to interactively control the focus during generation. Motivated by the classifier-free diffusion guidance, we form regular and unconditional context pairs based on highlighted tokens, demonstrating that the autoregressive generation in models can be guided in a classifier-free way. Notably, we find that, during inference, guiding the models with highlighted tokens through the attention weights leads to more desired outputs. Our approach is compatible with current LLMs and VLMs, achieving impressive customized generation results without training. Experiments confirm its effectiveness in focusing on input contexts and generating reliable content. Without tuning on LLaVA-v1.5, our method secured 69.5 in the MMBench test and 1552.5 in MME-perception. The code is available at: https://github.com/dvlab-research/Prompt-Highlighter/
Authors: Zuyao Chen, Jinlin Wu, Zhen Lei, Zhaoxiang Zhang, Changwen Chen
Learning scene graphs from natural language descriptions has proven to be a cheap and promising scheme for Scene Graph Generation (SGG). However, such unstructured caption data and its processing are troubling the learning an acurrate and complete scene graph. This dilema can be summarized as three points. First, traditional language parsers often fail to extract meaningful relationship triplets from caption data. Second, grounding unlocalized objects in parsed triplets will meet ambiguity in visual-language alignment. Last, caption data typically are sparse and exhibit bias to partial observations of image content. These three issues make it hard for the model to generate comprehensive and accurate scene graphs. To fill this gap, we propose a simple yet effective framework, GPT4SGG, to synthesize scene graphs from holistic and region-specific narratives. The framework discards traditional language parser, and localize objects before obtaining relationship triplets. To obtain relationship triplets, holistic and dense region-specific narratives are generated from the image. With such textual representation of image data and a task-specific prompt, an LLM, particularly GPT-4, directly synthesizes a scene graph as "pseudo labels". Experimental results showcase GPT4SGG significantly improves the performance of SGG models trained on image-caption data. We believe this pioneering work can motivate further research into mining the visual reasoning capabilities of LLMs.
Authors: Xin Li, Yeqi Bai, Pinlong Cai, Licheng Wen, Daocheng Fu, Bo Zhang, Xuemeng Yang, Xinyu Cai, Tao Ma, Jianfei Guo, Xing Gao, Min Dou, Botian Shi, Yong Liu, Liang He, Yu Qiao
This paper explores the emerging knowledge-driven autonomous driving technologies. Our investigation highlights the limitations of current autonomous driving systems, in particular their sensitivity to data bias, difficulty in handling long-tail scenarios, and lack of interpretability. Conversely, knowledge-driven methods with the abilities of cognition, generalization and life-long learning emerge as a promising way to overcome these challenges. This paper delves into the essence of knowledge-driven autonomous driving and examines its core components: dataset \& benchmark, environment, and driver agent. By leveraging large language models, world models, neural rendering, and other advanced artificial intelligence techniques, these components collectively contribute to a more holistic, adaptive, and intelligent autonomous driving system. The paper systematically organizes and reviews previous research efforts in this area, and provides insights and guidance for future research and practical applications of autonomous driving. We will continually share the latest updates on cutting-edge developments in knowledge-driven autonomous driving along with the relevant valuable open-source resources at: \url{https://github.com/PJLab-ADG/awesome-knowledge-driven-AD}.
Authors: Ruyi Gan, Xiaojun Wu, Junyu Lu, Yuanhe Tian, Dixiang Zhang, Ziwei Wu, Renliang Sun, Chang Liu, Jiaxing Zhang, Pingjian Zhang, Yan Song
With the open-sourcing of text-to-image models (T2I) such as stable diffusion (SD) and stable diffusion XL (SD-XL), there is an influx of models fine-tuned in specific domains based on the open-source SD model, such as in anime, character portraits, etc. However, there are few specialized models in certain domains, such as interior design, which is attributed to the complex textual descriptions and detailed visual elements inherent in design, alongside the necessity for adaptable resolution. Therefore, text-to-image models for interior design are required to have outstanding prompt-following capabilities, as well as iterative collaboration with design professionals to achieve the desired outcome. In this paper, we collect and optimize text-image data in the design field and continue training in both English and Chinese on the basis of the open-source CLIP model. We also proposed a fine-tuning strategy with curriculum learning and reinforcement learning from CLIP feedback to enhance the prompt-following capabilities of our approach so as to improve the quality of image generation. The experimental results on the collected dataset demonstrate the effectiveness of the proposed approach, which achieves impressive results and outperforms strong baselines.
Authors: Guang Yang, Jie Li, Hanxiao Lei, Xinbo Gao
Infrared and visible image fusion aims at generating a fused image containing the intensity and detail information of source images, and the key issue is effectively measuring and integrating the complementary information of multi-modality images from the same scene. Existing methods mostly adopt a simple weight in the loss function to decide the information retention of each modality rather than adaptively measuring complementary information for different image pairs. In this study, we propose a multi-scale dual attention (MDA) framework for infrared and visible image fusion, which is designed to measure and integrate complementary information in both structure and loss function at the image and patch level. In our method, the residual downsample block decomposes source images into three scales first. Then, dual attention fusion block integrates complementary information and generates a spatial and channel attention map at each scale for feature fusion. Finally, the output image is reconstructed by the residual reconstruction block. Loss function consists of image-level, feature-level and patch-level three parts, of which the calculation of the image-level and patch-level two parts are based on the weights generated by the complementary information measurement. Indeed, to constrain the pixel intensity distribution between the output and infrared image, a style loss is added. Our fusion results perform robust and informative across different scenarios. Qualitative and quantitative results on two datasets illustrate that our method is able to preserve both thermal radiation and detailed information from two modalities and achieve comparable results compared with the other state-of-the-art methods. Ablation experiments show the effectiveness of our information integration architecture and adaptively measure complementary information retention in the loss function.
Authors: Justine Giroux, Mohammad Reza Karimi Dastjerdi, Yannick Hold-Geoffroy, Javier Vazquez-Corral, Jean-François Lalonde
Progress in lighting estimation is tracked by computing existing image quality assessment (IQA) metrics on images from standard datasets. While this may appear to be a reasonable approach, we demonstrate that doing so does not correlate to human preference when the estimated lighting is used to relight a virtual scene into a real photograph. To study this, we design a controlled psychophysical experiment where human observers must choose their preference amongst rendered scenes lit using a set of lighting estimation algorithms selected from the recent literature, and use it to analyse how these algorithms perform according to human perception. Then, we demonstrate that none of the most popular IQA metrics from the literature, taken individually, correctly represent human perception. Finally, we show that by learning a combination of existing IQA metrics, we can more accurately represent human preference. This provides a new perceptual framework to help evaluate future lighting estimation algorithms.
Authors: Llukman Cerkezi, Aram Davtyan, Sepehr Sameni, Paolo Favaro
The growing interest in novel view synthesis, driven by Neural Radiance Field (NeRF) models, is hindered by scalability issues due to their reliance on precisely annotated multi-view images. Recent models address this by fine-tuning large text2image diffusion models on synthetic multi-view data. Despite robust zero-shot generalization, they may need post-processing and can face quality issues due to the synthetic-real domain gap. This paper introduces a novel pipeline for unsupervised training of a pose-conditioned diffusion model on single-category datasets. With the help of pretrained self-supervised Vision Transformers (DINOv2), we identify object poses by clustering the dataset through comparing visibility and locations of specific object parts. The pose-conditioned diffusion model, trained on pose labels, and equipped with cross-frame attention at inference time ensures cross-view consistency, that is further aided by our novel hard-attention guidance. Our model, MIRAGE, surpasses prior work in novel view synthesis on real images. Furthermore, MIRAGE is robust to diverse textures and geometries, as demonstrated with our experiments on synthetic images generated with pretrained Stable Diffusion.
Authors: Pengcheng Chen, Ziyan Huang, Zhongying Deng, Tianbin Li, Yanzhou Su, Haoyu Wang, Jin Ye, Yu Qiao, Junjun He
OpenAI's latest large vision-language model (LVLM), GPT-4V(ision), has piqued considerable interest for its potential in medical applications. Despite its promise, recent studies and internal reviews highlight its underperformance in specialized medical tasks. This paper explores the boundary of GPT-4V's capabilities in medicine, particularly in processing complex imaging data from endoscopies, CT scans, and MRIs etc. Leveraging open-source datasets, we assessed its foundational competencies, identifying substantial areas for enhancement. Our research emphasizes prompt engineering, an often-underutilized strategy for improving AI responsiveness. Through iterative testing, we refined the model's prompts, significantly improving its interpretative accuracy and relevance in medical imaging. From our comprehensive evaluations, we distilled 10 effective prompt engineering techniques, each fortifying GPT-4V's medical acumen. These methodical enhancements facilitate more reliable, precise, and clinically valuable insights from GPT-4V, advancing its operability in critical healthcare environments. Our findings are pivotal for those employing AI in medicine, providing clear, actionable guidance on harnessing GPT-4V's full diagnostic potential.
Authors: Dar-Yen Chen, Subhadeep Koley, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Ayan Kumar Bhunia, Yi-Zhe Song
In this paper, we democratise caricature generation, empowering individuals to effortlessly craft personalised caricatures with just a photo and a conceptual sketch. Our objective is to strike a delicate balance between abstraction and identity, while preserving the creativity and subjectivity inherent in a sketch. To achieve this, we present Explicit Rank-1 Model Editing alongside single-image personalisation, selectively applying nuanced edits to cross-attention layers for a seamless merge of identity and style. Additionally, we propose Random Mask Reconstruction to enhance robustness, directing the model to focus on distinctive identity and style features. Crucially, our aim is not to replace artists but to eliminate accessibility barriers, allowing enthusiasts to engage in the artistry.
Authors: Sijing Wu, Yunhao Li, Weitian Zhang, Jun Jia, Yucheng Zhu, Yichao Yan, Guangtao Zhai
Singing, as a common facial movement second only to talking, can be regarded as a universal language across ethnicities and cultures, plays an important role in emotional communication, art, and entertainment. However, it is often overlooked in the field of audio-driven facial animation due to the lack of singing head datasets and the domain gap between singing and talking in rhythm and amplitude. To this end, we collect a high-quality large-scale singing head dataset, SingingHead, which consists of more than 27 hours of synchronized singing video, 3D facial motion, singing audio, and background music from 76 individuals and 8 types of music. Along with the SingingHead dataset, we argue that 3D and 2D facial animation tasks can be solved together, and propose a unified singing facial animation framework named UniSinger to achieve both singing audio-driven 3D singing head animation and 2D singing portrait video synthesis. Extensive comparative experiments with both SOTA 3D facial animation and 2D portrait animation methods demonstrate the necessity of singing-specific datasets in singing head animation tasks and the promising performance of our unified facial animation framework.
Authors: Zejun Wu, Samuel W. Remedios, Blake E. Dewey, Aaron Carass, Jerry L. Prince
Anisotropic low-resolution (LR) magnetic resonance (MR) images are fast to obtain but hinder automated processing. We propose to use denoising diffusion probabilistic models (DDPMs) to super-resolve these 2D-acquired LR MR slices. This paper introduces AniRes2D, a novel approach combining DDPM with a residual prediction for 2D super-resolution (SR). Results demonstrate that AniRes2D outperforms several other DDPM-based models in quantitative metrics, visual quality, and out-of-domain evaluation. We use a trained AniRes2D to super-resolve 3D volumes slice by slice, where comparative quantitative results and reduced skull aliasing are achieved compared to a recent state-of-the-art self-supervised 3D super-resolution method. Furthermore, we explored the use of noise conditioning augmentation (NCA) as an alternative augmentation technique for DDPM-based SR models, but it was found to reduce performance. Our findings contribute valuable insights to the application of DDPMs for SR of anisotropic MR images.
Authors: Yinhuai Wang, Jing Lin, Ailing Zeng, Zhengyi Luo, Jian Zhang, Lei Zhang
Humans interact with objects all the time. Enabling a humanoid to learn human-object interaction (HOI) is a key step for future smart animation and intelligent robotics systems. However, recent progress in physics-based HOI requires carefully designed task-specific rewards, making the system unscalable and labor-intensive. This work focuses on dynamic HOI imitation: teaching humanoid dynamic interaction skills through imitating kinematic HOI demonstrations. It is quite challenging because of the complexity of the interaction between body parts and objects and the lack of dynamic HOI data. To handle the above issues, we present PhysHOI, the first physics-based whole-body HOI imitation approach without task-specific reward designs. Except for the kinematic HOI representations of humans and objects, we introduce the contact graph to model the contact relations between body parts and objects explicitly. A contact graph reward is also designed, which proved to be critical for precise HOI imitation. Based on the key designs, PhysHOI can imitate diverse HOI tasks simply yet effectively without prior knowledge. To make up for the lack of dynamic HOI scenarios in this area, we introduce the BallPlay dataset that contains eight whole-body basketball skills. We validate PhysHOI on diverse HOI tasks, including whole-body grasping and basketball skills.
Authors: Yongqi Dong, Xingmin Lu, Ruohan Li, Wei Song, Bart van Arem, Haneen Farah
The burgeoning navigation services using digital maps provide great convenience to drivers. Nevertheless, the presence of anomalies in lane rendering map images occasionally introduces potential hazards, as such anomalies can be misleading to human drivers and consequently contribute to unsafe driving conditions. In response to this concern and to accurately and effectively detect the anomalies, this paper transforms lane rendering image anomaly detection into a classification problem and proposes a four-phase pipeline consisting of data pre-processing, self-supervised pre-training with the masked image modeling (MiM) method, customized fine-tuning using cross-entropy based loss with label smoothing, and post-processing to tackle it leveraging state-of-the-art deep learning techniques, especially those involving Transformer models. Various experiments verify the effectiveness of the proposed pipeline. Results indicate that the proposed pipeline exhibits superior performance in lane rendering image anomaly detection, and notably, the self-supervised pre-training with MiM can greatly enhance the detection accuracy while significantly reducing the total training time. For instance, employing the Swin Transformer with Uniform Masking as self-supervised pretraining (Swin-Trans-UM) yielded a heightened accuracy at 94.77% and an improved Area Under The Curve (AUC) score of 0.9743 compared with the pure Swin Transformer without pre-training (Swin-Trans) with an accuracy of 94.01% and an AUC of 0.9498. The fine-tuning epochs were dramatically reduced to 41 from the original 280. In conclusion, the proposed pipeline, with its incorporation of self-supervised pre-training using MiM and other advanced deep learning techniques, emerges as a robust solution for enhancing the accuracy and efficiency of lane rendering image anomaly detection in digital navigation systems.
Authors: Dongchen Han, Xiaojun Jia, Yang Bai, Jindong Gu, Yang Liu, Xiaochun Cao
Vision-language pre-training (VLP) models demonstrate impressive abilities in processing both images and text. However, they are vulnerable to multi-modal adversarial examples (AEs). Investigating the generation of high-transferability adversarial examples is crucial for uncovering VLP models' vulnerabilities in practical scenarios. Recent works have indicated that leveraging data augmentation and image-text modal interactions can enhance the transferability of adversarial examples for VLP models significantly. However, they do not consider the optimal alignment problem between dataaugmented image-text pairs. This oversight leads to adversarial examples that are overly tailored to the source model, thus limiting improvements in transferability. In our research, we first explore the interplay between image sets produced through data augmentation and their corresponding text sets. We find that augmented image samples can align optimally with certain texts while exhibiting less relevance to others. Motivated by this, we propose an Optimal Transport-based Adversarial Attack, dubbed OT-Attack. The proposed method formulates the features of image and text sets as two distinct distributions and employs optimal transport theory to determine the most efficient mapping between them. This optimal mapping informs our generation of adversarial examples to effectively counteract the overfitting issues. Extensive experiments across various network architectures and datasets in image-text matching tasks reveal that our OT-Attack outperforms existing state-of-the-art methods in terms of adversarial transferability.
Authors: Jiayi Guo, Xingqian Xu, Yifan Pu, Zanlin Ni, Chaofei Wang, Manushree Vasu, Shiji Song, Gao Huang, Humphrey Shi
Recently, diffusion models have made remarkable progress in text-to-image (T2I) generation, synthesizing images with high fidelity and diverse contents. Despite this advancement, latent space smoothness within diffusion models remains largely unexplored. Smooth latent spaces ensure that a perturbation on an input latent corresponds to a steady change in the output image. This property proves beneficial in downstream tasks, including image interpolation, inversion, and editing. In this work, we expose the non-smoothness of diffusion latent spaces by observing noticeable visual fluctuations resulting from minor latent variations. To tackle this issue, we propose Smooth Diffusion, a new category of diffusion models that can be simultaneously high-performing and smooth. Specifically, we introduce Step-wise Variation Regularization to enforce the proportion between the variations of an arbitrary input latent and that of the output image is a constant at any diffusion training step. In addition, we devise an interpolation standard deviation (ISTD) metric to effectively assess the latent space smoothness of a diffusion model. Extensive quantitative and qualitative experiments demonstrate that Smooth Diffusion stands out as a more desirable solution not only in T2I generation but also across various downstream tasks. Smooth Diffusion is implemented as a plug-and-play Smooth-LoRA to work with various community models. Code is available at https://github.com/SHI-Labs/Smooth-Diffusion.
Authors: Yabo Chen, Jiemin Fang, Yuyang Huang, Taoran Yi, Xiaopeng Zhang, Lingxi Xie, Xinggang Wang, Wenrui Dai, Hongkai Xiong, Qi Tian
Synthesizing multi-view 3D from one single image is a significant and challenging task. For this goal, Zero-1-to-3 methods aim to extend a 2D latent diffusion model to the 3D scope. These approaches generate the target-view image with a single-view source image and the camera pose as condition information. However, the one-to-one manner adopted in Zero-1-to-3 incurs challenges for building geometric and visual consistency across views, especially for complex objects. We propose a cascade generation framework constructed with two Zero-1-to-3 models, named Cascade-Zero123, to tackle this issue, which progressively extracts 3D information from the source image. Specifically, a self-prompting mechanism is designed to generate several nearby views at first. These views are then fed into the second-stage model along with the source image as generation conditions. With self-prompted multiple views as the supplementary information, our Cascade-Zero123 generates more highly consistent novel-view images than Zero-1-to-3. The promotion is significant for various complex and challenging scenes, involving insects, humans, transparent objects, and stacked multiple objects etc. The project page is at https://cascadezero123.github.io/.
Authors: Shubham Agarwal, Subrata Mitra, Sarthak Chakraborty, Srikrishna Karanam, Koyel Mukherjee, Shiv Saini
Text-to-image generation using diffusion models has seen explosive popularity owing to their ability in producing high quality images adhering to text prompts. However, production-grade diffusion model serving is a resource intensive task that not only require high-end GPUs which are expensive but also incurs considerable latency. In this paper, we introduce a technique called approximate-caching that can reduce such iterative denoising steps for an image generation based on a prompt by reusing intermediate noise states created during a prior image generation for similar prompts. Based on this idea, we present an end to end text-to-image system, Nirvana, that uses the approximate-caching with a novel cache management-policy Least Computationally Beneficial and Frequently Used (LCBFU) to provide % GPU compute savings, 19.8% end-to-end latency reduction and 19% dollar savings, on average, on two real production workloads. We further present an extensive characterization of real production text-to-image prompts from the perspective of caching, popularity and reuse of intermediate states in a large production environment.
Authors: Yujie Wei, Shiwei Zhang, Zhiwu Qing, Hangjie Yuan, Zhiheng Liu, Yu Liu, Yingya Zhang, Jingren Zhou, Hongming Shan
Customized generation using diffusion models has made impressive progress in image generation, but remains unsatisfactory in the challenging video generation task, as it requires the controllability of both subjects and motions. To that end, we present DreamVideo, a novel approach to generating personalized videos from a few static images of the desired subject and a few videos of target motion. DreamVideo decouples this task into two stages, subject learning and motion learning, by leveraging a pre-trained video diffusion model. The subject learning aims to accurately capture the fine appearance of the subject from provided images, which is achieved by combining textual inversion and fine-tuning of our carefully designed identity adapter. In motion learning, we architect a motion adapter and fine-tune it on the given videos to effectively model the target motion pattern. Combining these two lightweight and efficient adapters allows for flexible customization of any subject with any motion. Extensive experimental results demonstrate the superior performance of our DreamVideo over the state-of-the-art methods for customized video generation. Our project page is at https://dreamvideo-t2v.github.io.
Authors: Annika Reinke, Minu D. Tizabi, Carole H. Sudre, Matthias Eisenmann, Tim Rädsch, Michael Baumgartner, Laura Acion, Michela Antonelli, Tal Arbel, Spyridon Bakas, Peter Bankhead, Arriel Benis, Matthew Blaschko, Florian Buettner, M. Jorge Cardoso, Jianxu Chen, Veronika Cheplygina, Evangelia Christodoulou, Beth Cimini, Gary S. Collins, Sandy Engelhardt, Keyvan Farahani, Luciana Ferrer, Adrian Galdran, Bram van Ginneken, Ben Glocker, Patrick Godau, Robert Haase, Fred Hamprecht, Daniel A. Hashimoto, Doreen Heckmann-Nötzel, Peter Hirsch, Michael M. Hoffman, Merel Huisman, Fabian Isensee, Pierre Jannin, Charles E. Kahn, Dagmar Kainmueller, Bernhard Kainz, Alexandros Karargyris, Alan Karthikesalingam, A. Emre Kavur, Hannes Kenngott, Jens Kleesiek, Andreas Kleppe, Sven Kohler, Florian Kofler, et al. (46 additional authors not shown)
While the importance of automatic image analysis is continuously increasing, recent meta-research revealed major flaws with respect to algorithm validation. Performance metrics are particularly key for meaningful, objective, and transparent performance assessment and validation of the used automatic algorithms, but relatively little attention has been given to the practical pitfalls when using specific metrics for a given image analysis task. These are typically related to (1) the disregard of inherent metric properties, such as the behaviour in the presence of class imbalance or small target structures, (2) the disregard of inherent data set properties, such as the non-independence of the test cases, and (3) the disregard of the actual biomedical domain interest that the metrics should reflect. This living dynamically document has the purpose to illustrate important limitations of performance metrics commonly applied in the field of image analysis. In this context, it focuses on biomedical image analysis problems that can be phrased as image-level classification, semantic segmentation, instance segmentation, or object detection task. The current version is based on a Delphi process on metrics conducted by an international consortium of image analysis experts from more than 60 institutions worldwide.
Authors: Evgenia Rusak, Steffen Schneider, George Pachitariu, Luisa Eck, Peter Gehler, Oliver Bringmann, Wieland Brendel, Matthias Bethge
We demonstrate that self-learning techniques like entropy minimization and pseudo-labeling are simple and effective at improving performance of a deployed computer vision model under systematic domain shifts. We conduct a wide range of large-scale experiments and show consistent improvements irrespective of the model architecture, the pre-training technique or the type of distribution shift. At the same time, self-learning is simple to use in practice because it does not require knowledge or access to the original training data or scheme, is robust to hyperparameter choices, is straight-forward to implement and requires only a few adaptation epochs. This makes self-learning techniques highly attractive for any practitioner who applies machine learning algorithms in the real world. We present state-of-the-art adaptation results on CIFAR10-C (8.5% error), ImageNet-C (22.0% mCE), ImageNet-R (17.4% error) and ImageNet-A (14.8% error), theoretically study the dynamics of self-supervised adaptation methods and propose a new classification dataset (ImageNet-D) which is challenging even with adaptation.
Authors: Tianyue Zheng, Zhe Chen, Shuya Ding, Chao Cai, Jun Luo
Whereas adversarial training can be useful against specific adversarial perturbations, they have also proven ineffective in generalizing towards attacks deviating from those used for training. However, we observe that this ineffectiveness is intrinsically connected to domain adaptability, another crucial issue in deep learning for which adversarial domain adaptation appears to be a promising solution. Consequently, we proposed Adv-4-Adv as a novel adversarial training method that aims to retain robustness against unseen adversarial perturbations. Essentially, Adv-4-Adv treats attacks incurring different perturbations as distinct domains, and by leveraging the power of adversarial domain adaptation, it aims to remove the domain/attack-specific features. This forces a trained model to learn a robust domain-invariant representation, which in turn enhances its generalization ability. Extensive evaluations on Fashion-MNIST, SVHN, CIFAR-10, and CIFAR-100 demonstrate that a model trained by Adv-4-Adv based on samples crafted by simple attacks (e.g., FGSM) can be generalized to more advanced attacks (e.g., PGD), and the performance exceeds state-of-the-art proposals on these datasets.
Authors: Jaehui Hwang, Huan Zhang, Jun-Ho Choi, Cho-Jui Hsieh, Jong-Seok Lee
Recently, video-based action recognition methods using convolutional neural networks (CNNs) achieve remarkable recognition performance. However, there is still lack of understanding about the generalization mechanism of action recognition models. In this paper, we suggest that action recognition models rely on the motion information less than expected, and thus they are robust to randomization of frame orders. Furthermore, we find that motion monotonicity remaining after randomization also contributes to such robustness. Based on this observation, we develop a novel defense method using temporal shuffling of input videos against adversarial attacks for action recognition models. Another observation enabling our defense method is that adversarial perturbations on videos are sensitive to temporal destruction. To the best of our knowledge, this is the first attempt to design a defense method without additional training for 3D CNN-based video action recognition models.
Authors: Zeev Gutman, Ritvik Vij (IIT Delhi), Laurent Najman (LIGM), Michael Lindenbaum
Current approaches to generic segmentation start by creating a hierarchy of nested image partitions and then specifying a segmentation from it. Our first contribution is to describe several ways, most of them new, for specifying segmentations using the hierarchy elements. Then, we consider the best hierarchy-induced segmentation specified by a limited number of hierarchy elements. We focus on a common quality measure for binary segmentations, the Jaccard index (also known as IoU). Optimizing the Jaccard index is highly non-trivial, and yet we propose an efficient approach for doing exactly that. This way we get algorithm-independent upper bounds on the quality of any segmentation created from the hierarchy. We found that the obtainable segmentation quality varies significantly depending on the way that the segments are specified by the hierarchy elements, and that representing a segmentation with only a few hierarchy elements is often possible. (Code is available).
Authors: Dinghao Yang, Bin Wang, Weijia Li, Yiqi Lin, Conghui He
Recent image matting studies are developing towards proposing trimap-free or interactive methods for complete complex image matting tasks. Although avoiding the extensive labors of trimap annotation, existing methods still suffer from two limitations: (1) For the single image with multiple objects, it is essential to provide extra interaction information to help determining the matting target; (2) For transparent objects, the accurate regression of alpha matte from RGB image is much more difficult compared with the opaque ones. In this work, we propose a Unified Interactive image Matting method, named UIM, which solves the limitations and achieves satisfying matting results for any scenario. Specifically, UIM leverages multiple types of user interaction to avoid the ambiguity of multiple matting targets, and we compare the pros and cons of different annotation types in detail. To unify the matting performance for transparent and opaque objects, we decouple image matting into two stages, i.e., foreground segmentation and transparency prediction. Moreover, we design a multi-scale attentive fusion module to alleviate the vagueness in the boundary region. Experimental results demonstrate that UIM achieves state-of-the-art performance on the Composition-1K test set and a synthetic unified dataset.
Authors: Nick McGreivy, Ammar Hakim
The purpose of this short and simple note is to clarify a common misconception about convolutional neural networks (CNNs). CNNs are made up of convolutional layers which are shift equivariant due to weight sharing. However, convolutional layers are not translation equivariant, even when boundary effects are ignored and when pooling and subsampling are absent. This is because shift equivariance is a discrete symmetry while translation equivariance is a continuous symmetry. This fact is well known among researchers in equivariant machine learning, but is usually overlooked among non-experts. To minimize confusion, we suggest using the term `shift equivariance' to refer to discrete shifts in pixels and `translation equivariance' to refer to continuous translations.
Authors: Daizong Liu, Wei Hu, Xin Li
With the increasing attention in various 3D safety-critical applications, point cloud learning models have been shown to be vulnerable to adversarial attacks. Although existing 3D attack methods achieve high success rates, they delve into the data space with point-wise perturbation, which may neglect the geometric characteristics. Instead, we propose point cloud attacks from a new perspective -- the graph spectral domain attack, aiming to perturb graph transform coefficients in the spectral domain that corresponds to varying certain geometric structure. Specifically, leveraging on graph signal processing, we first adaptively transform the coordinates of points onto the spectral domain via graph Fourier transform (GFT) for compact representation. Then, we analyze the influence of different spectral bands on the geometric structure, based on which we propose to perturb the GFT coefficients via a learnable graph spectral filter. Considering the low-frequency components mainly contribute to the rough shape of the 3D object, we further introduce a low-frequency constraint to limit perturbations within imperceptible high-frequency components. Finally, the adversarial point cloud is generated by transforming the perturbed spectral representation back to the data domain via the inverse GFT. Experimental results demonstrate the effectiveness of the proposed attack in terms of both the imperceptibility and attack success rates.
Authors: Samuel Dooley, Rhea Sanjay Sukthanker, John P. Dickerson, Colin White, Frank Hutter, Micah Goldblum
Face recognition systems are widely deployed in safety-critical applications, including law enforcement, yet they exhibit bias across a range of socio-demographic dimensions, such as gender and race. Conventional wisdom dictates that model biases arise from biased training data. As a consequence, previous works on bias mitigation largely focused on pre-processing the training data, adding penalties to prevent bias from effecting the model during training, or post-processing predictions to debias them, yet these approaches have shown limited success on hard problems such as face recognition. In our work, we discover that biases are actually inherent to neural network architectures themselves. Following this reframing, we conduct the first neural architecture search for fairness, jointly with a search for hyperparameters. Our search outputs a suite of models which Pareto-dominate all other high-performance architectures and existing bias mitigation methods in terms of accuracy and fairness, often by large margins, on the two most widely used datasets for face identification, CelebA and VGGFace2. Furthermore, these models generalize to other datasets and sensitive attributes. We release our code, models and raw data files at https://github.com/dooleys/FR-NAS.
Authors: Jaehui Hwang, Dongyoon Han, Byeongho Heo, Song Park, Sanghyuk Chun, Jong-Seok Lee
In recent years, many deep neural architectures have been developed for image classification. Whether they are similar or dissimilar and what factors contribute to their (dis)similarities remains curious. To address this question, we aim to design a quantitative and scalable similarity measure between neural architectures. We propose Similarity by Attack Transferability (SAT) from the observation that adversarial attack transferability contains information related to input gradients and decision boundaries widely used to understand model behaviors. We conduct a large-scale analysis on 69 state-of-the-art ImageNet classifiers using our proposed similarity function to answer the question. Moreover, we observe neural architecture-related phenomena using model similarity that model diversity can lead to better performance on model ensembles and knowledge distillation under specific conditions. Our results provide insights into why developing diverse neural architectures with distinct components is necessary.
Authors: Anna Breger, Clemens Karner, Martin Ehler
We present a novel clustering algorithm, visClust, that is based on lower dimensional data representations and visual interpretation. Thereto, we design a transformation that allows the data to be represented by a binary integer array enabling the use of image processing methods to select a partition. Qualitative and quantitative analyses measured in accuracy and an adjusted Rand-Index show that the algorithm performs well while requiring low runtime and RAM. We compare the results to 6 state-of-the-art algorithms with available code, confirming the quality of visClust by superior performance in most experiments. Moreover, the algorithm asks for just one obligatory input parameter while allowing optimization via optional parameters. The code is made available on GitHub and straightforward to use.
Authors: Soumya Jahagirdar, Minesh Mathew, Dimosthenis Karatzas, C. V. Jawahar
Video Question Answering methods focus on commonsense reasoning and visual cognition of objects or persons and their interactions over time. Current VideoQA approaches ignore the textual information present in the video. Instead, we argue that textual information is complementary to the action and provides essential contextualisation cues to the reasoning process. To this end, we propose a novel VideoQA task that requires reading and understanding the text in the video. To explore this direction, we focus on news videos and require QA systems to comprehend and answer questions about the topics presented by combining visual and textual cues in the video. We introduce the ``NewsVideoQA'' dataset that comprises more than $8,600$ QA pairs on $3,000+$ news videos obtained from diverse news channels from around the world. We demonstrate the limitations of current Scene Text VQA and VideoQA methods and propose ways to incorporate scene text information into VideoQA methods.
Authors: Henry Kvinge, Grayson Jorgenson, Davis Brown, Charles Godfrey, Tegan Emerson
While the last five years have seen considerable progress in understanding the internal representations of deep learning models, many questions remain. This is especially true when trying to understand the impact of model design choices, such as model architecture or training algorithm, on hidden representation geometry and dynamics. In this work we present a new approach to studying such representations inspired by the idea of a frame on the tangent bundle of a manifold. Our construction, which we call a neural frame, is formed by assembling a set of vectors representing specific types of perturbations of a data point, for example infinitesimal augmentations, noise perturbations, or perturbations produced by a generative model, and studying how these change as they pass through a network. Using neural frames, we make observations about the way that models process, layer-by-layer, specific modes of variation within a small neighborhood of a datapoint. Our results provide new perspectives on a number of phenomena, such as the manner in which training with augmentation produces model invariance or the proposed trade-off between adversarial training and model generalization.
Authors: Harry Freeman, Mohamad Qadri, Abhisesh Silwal, Paul O'Connor, Zachary Rubinstein, Daniel Cooley, George Kantor
In this paper, we present a computer vision-based approach to measure the sizes and growth rates of apple fruitlets. Measuring the growth rates of apple fruitlets is important because it allows apple growers to determine when to apply chemical thinners to their crops in order to optimize yield. The current practice of obtaining growth rates involves using calipers to record sizes of fruitlets across multiple days. Due to the number of fruitlets needed to be sized, this method is laborious, time-consuming, and prone to human error. With images collected by a hand-held stereo camera, our system, segments, clusters, and fits ellipses to fruitlets to measure their diameters. The growth rates are then calculated by temporally associating clustered fruitlets across days. We provide quantitative results on data collected in an apple orchard, and demonstrate that our system is able to predict abscise rates within 3.5% of the current method with a 6 times improvement in speed, while requiring significantly less manual effort. Moreover, we provide results on images captured by a robotic system in the field, and discuss the next steps required to make the process fully autonomous.
Authors: Roei Herzig, Ofir Abramovich, Elad Ben-Avraham, Assaf Arbelle, Leonid Karlinsky, Ariel Shamir, Trevor Darrell, Amir Globerson
Action recognition models have achieved impressive results by incorporating scene-level annotations, such as objects, their relations, 3D structure, and more. However, obtaining annotations of scene structure for videos requires a significant amount of effort to gather and annotate, making these methods expensive to train. In contrast, synthetic datasets generated by graphics engines provide powerful alternatives for generating scene-level annotations across multiple tasks. In this work, we propose an approach to leverage synthetic scene data for improving video understanding. We present a multi-task prompt learning approach for video transformers, where a shared video transformer backbone is enhanced by a small set of specialized parameters for each task. Specifically, we add a set of "task prompts", each corresponding to a different task, and let each prompt predict task-related annotations. This design allows the model to capture information shared among synthetic scene tasks as well as information shared between synthetic scene tasks and a real video downstream task throughout the entire network. We refer to this approach as "Promptonomy", since the prompts model task-related structure. We propose the PromptonomyViT model (PViT), a video transformer that incorporates various types of scene-level information from synthetic data using the "Promptonomy" approach. PViT shows strong performance improvements on multiple video understanding tasks and datasets. Project page: \url{https://ofir1080.github.io/PromptonomyViT}
Authors: Georg Krispel, David Schinagl, Christian Fruhwirth-Reisinger, Horst Possegger, Horst Bischof
The sensing process of large-scale LiDAR point clouds inevitably causes large blind spots, i.e. regions not visible to the sensor. We demonstrate how these inherent sampling properties can be effectively utilized for self-supervised representation learning by designing a highly effective pre-training framework that considerably reduces the need for tedious 3D annotations to train state-of-the-art object detectors. Our Masked AutoEncoder for LiDAR point clouds (MAELi) intuitively leverages the sparsity of LiDAR point clouds in both the encoder and decoder during reconstruction. This results in more expressive and useful initialization, which can be directly applied to downstream perception tasks, such as 3D object detection or semantic segmentation for autonomous driving. In a novel reconstruction approach, MAELi distinguishes between empty and occluded space and employs a new masking strategy that targets the LiDAR's inherent spherical projection. Thereby, without any ground truth whatsoever and trained on single frames only, MAELi obtains an understanding of the underlying 3D scene geometry and semantics. To demonstrate the potential of MAELi, we pre-train backbones in an end-to-end manner and show the effectiveness of our unsupervised pre-trained weights on the tasks of 3D object detection and semantic segmentation.
Authors: Shoki Ohta, Takayuki Nishio, Riichi Kudo, Kahoko Takahashi, Hisashi Nagata
This study demonstrates the feasibility of point cloud-based proactive link quality prediction for millimeter-wave (mmWave) communications. Previous studies have proposed machine learning-based methods to predict received signal strength for future time periods using time series of depth images to mitigate the line-of-sight (LOS) path blockage by pedestrians in mmWave communication. However, these image-based methods have limited applicability due to privacy concerns as camera images may contain sensitive information. This study proposes a point cloud-based method for mmWave link quality prediction and demonstrates its feasibility through experiments. Point clouds represent three-dimensional (3D) spaces as a set of points and are sparser and less likely to contain sensitive information than camera images. Additionally, point clouds provide 3D position and motion information, which is necessary for understanding the radio propagation environment involving pedestrians. This study designs the mmWave link quality prediction method and conducts realistic indoor experiments, where the link quality fluctuates significantly due to human blockage, using commercially available IEEE 802.11ad-based 60 GHz wireless LAN devices and Kinect v2 RGB-D camera and Velodyne VLP-16 light detection and ranging (LiDAR) for point cloud acquisition. The experimental results showed that our proposed method can predict future large attenuation of mmWave received signal strength and throughput induced by the LOS path blockage by pedestrians with comparable or superior accuracy to image-based prediction methods. Hence, our point cloud-based method can serve as a viable alternative to image-based methods.
Authors: Ni Yao, Yanhui Tian, Daniel Gama das Neves, Chen Zhao, Claudio Tinoco Mesquita, Wolney de Andrade Martins, Alair Augusto Sarmet Moreira Damas dos Santos, Yanting Li, Chuang Han, Fubao Zhu, Neng Dai, Weihua Zhou
Epicardial adipose tissue (EAT) is known for its pro-inflammatory properties and association with Coronavirus Disease 2019 (COVID-19) severity. However, current EAT segmentation methods do not consider positional information. Additionally, the detection of COVID-19 severity lacks consideration for EAT radiomics features, which limits interpretability. This study investigates the use of radiomics features from EAT and lungs to detect the severity of COVID-19 infections. A retrospective analysis of 515 patients with COVID-19 (Cohort1: 415, Cohort2: 100) was conducted using a proposed three-stage deep learning approach for EAT extraction. Lung segmentation was achieved using a published method. A hybrid model for detecting the severity of COVID-19 was built in a derivation cohort, and its performance and uncertainty were evaluated in internal (125, Cohort1) and external (100, Cohort2) validation cohorts. For EAT extraction, the Dice similarity coefficients (DSC) of the two centers were 0.972 (+-0.011) and 0.968 (+-0.005), respectively. For severity detection, the hybrid model with radiomics features of both lungs and EAT showed improvements in AUC, net reclassification improvement (NRI), and integrated discrimination improvement (IDI) compared to the model with only lung radiomics features. The hybrid model exhibited an increase of 0.1 (p<0.001), 19.3%, and 18.0% respectively, in the internal validation cohort and an increase of 0.09 (p<0.001), 18.0%, and 18.0%, respectively, in the external validation cohort while outperforming existing detection methods. Uncertainty quantification and radiomics features analysis confirmed the interpretability of case prediction after inclusion of EAT features.
Authors: Zhaoxi Chen, Guangcong Wang, Ziwei Liu
In this work, we present SceneDreamer, an unconditional generative model for unbounded 3D scenes, which synthesizes large-scale 3D landscapes from random noise. Our framework is learned from in-the-wild 2D image collections only, without any 3D annotations. At the core of SceneDreamer is a principled learning paradigm comprising 1) an efficient yet expressive 3D scene representation, 2) a generative scene parameterization, and 3) an effective renderer that can leverage the knowledge from 2D images. Our approach begins with an efficient bird's-eye-view (BEV) representation generated from simplex noise, which includes a height field for surface elevation and a semantic field for detailed scene semantics. This BEV scene representation enables 1) representing a 3D scene with quadratic complexity, 2) disentangled geometry and semantics, and 3) efficient training. Moreover, we propose a novel generative neural hash grid to parameterize the latent space based on 3D positions and scene semantics, aiming to encode generalizable features across various scenes. Lastly, a neural volumetric renderer, learned from 2D image collections through adversarial training, is employed to produce photorealistic images. Extensive experiments demonstrate the effectiveness of SceneDreamer and superiority over state-of-the-art methods in generating vivid yet diverse unbounded 3D worlds.
Authors: Yiran Xu, Zhixin Shu, Cameron Smith, Seoung Wug Oh, Jia-Bin Huang
3D-aware GANs offer new capabilities for view synthesis while preserving the editing functionalities of their 2D counterparts. GAN inversion is a crucial step that seeks the latent code to reconstruct input images or videos, subsequently enabling diverse editing tasks through manipulation of this latent code. However, a model pre-trained on a particular dataset (e.g., FFHQ) often has difficulty reconstructing images with out-of-distribution (OOD) objects such as faces with heavy make-up or occluding objects. We address this issue by explicitly modeling OOD objects from the input in 3D-aware GANs. Our core idea is to represent the image using two individual neural radiance fields: one for the in-distribution content and the other for the out-of-distribution object. The final reconstruction is achieved by optimizing the composition of these two radiance fields with carefully designed regularization. We demonstrate that our explicit decomposition alleviates the inherent trade-off between reconstruction fidelity and editability. We evaluate reconstruction accuracy and editability of our method on challenging real face images and videos and showcase favorable results against other baselines.
Authors: Fatin E. M. Al-Obaidi, Anwar H. Al-Saleh, Shaymaa H. Kafi, Ali J.Karam, Ali A. D. Al-Zuky
The normalized 2-D correlation technique is a robust method for detecting targets in images due to its ability to remain invariant under rotation, translation, and scaling. This paper examines the impact of translation, and scaling on target identification in images. The results indicate a high level of accuracy in detecting targets, even when they are exhibit variations in location and size. The results indicate that the similarity between the image and the two used targets improves as the resize ratio increases. All statistical estimators demonstrate a strong similarity between the original and extracted targets. The elapsed time for all scenarios falls within the range (44.75-44.85), (37.48-37.73) seconds for bird and children targets respectively, and the correlation coefficient displays stable relationships with values that fall within the range of (0.90-0.98) and (0.87-0.93) for bird and children targets respectively.
Authors: Marcel Grimmer, Christian Rathgeb, Christoph Busch
Evaluating the quality of facial images is essential for operating face recognition systems with sufficient accuracy. The recent advances in face quality standardisation (ISO/IEC CD3 29794-5) recommend the usage of component quality measures for breaking down face quality into its individual factors, hence providing valuable feedback for operators to re-capture low-quality images. In light of recent advances in 3D-aware generative adversarial networks, we propose a novel dataset, Syn-YawPitch, comprising 1000 identities with varying yaw-pitch angle combinations. Utilizing this dataset, we demonstrate that pitch angles beyond 30 degrees have a significant impact on the biometric performance of current face recognition systems. Furthermore, we propose a lightweight and explainable pose quality predictor that adheres to the draft international standard of ISO/IEC CD3 29794-5 and benchmark it against state-of-the-art face image quality assessment algorithms
Authors: Bang Yang, Fenglin Liu, Yuexian Zou, Xian Wu, Yaowei Wang, David A. Clifton
Natural Language Generation (NLG) accepts input data in the form of images, videos, or text and generates corresponding natural language text as output. Existing NLG methods mainly adopt a supervised approach and rely heavily on coupled data-to-text pairs. However, for many targeted scenarios and for non-English languages, sufficient quantities of labeled data are often not available. To relax the dependency on labeled data of downstream tasks, we propose an intuitive and effective zero-shot learning framework, ZeroNLG, which can deal with multiple NLG tasks, including image-to-text (image captioning), video-to-text (video captioning), and text-to-text (neural machine translation), across English, Chinese, German, and French within a unified framework. ZeroNLG does not require any labeled downstream pairs for training. During training, ZeroNLG (i) projects different domains (across modalities and languages) to corresponding coordinates in a shared common latent space; (ii) bridges different domains by aligning their corresponding coordinates in this space; and (iii) builds an unsupervised multilingual auto-encoder to learn to generate text by reconstructing the input text given its coordinate in shared latent space. Consequently, during inference, based on the data-to-text pipeline, ZeroNLG can generate target sentences across different languages given the coordinate of input data in the common space. Within this unified framework, given visual (imaging or video) data as input, ZeroNLG can perform zero-shot visual captioning; given textual sentences as input, ZeroNLG can perform zero-shot machine translation. We present the results of extensive experiments on twelve NLG tasks, showing that, without using any labeled downstream pairs for training, ZeroNLG generates high-quality and believable outputs and significantly outperforms existing zero-shot methods.
Authors: Willi Menapace, Aliaksandr Siarohin, Stéphane Lathuilière, Panos Achlioptas, Vladislav Golyanik, Sergey Tulyakov, Elisa Ricci
Neural video game simulators emerged as powerful tools to generate and edit videos. Their idea is to represent games as the evolution of an environment's state driven by the actions of its agents. While such a paradigm enables users to play a game action-by-action, its rigidity precludes more semantic forms of control. To overcome this limitation, we augment game models with prompts specified as a set of natural language actions and desired states. The result-a Promptable Game Model (PGM)-makes it possible for a user to play the game by prompting it with high- and low-level action sequences. Most captivatingly, our PGM unlocks the director's mode, where the game is played by specifying goals for the agents in the form of a prompt. This requires learning "game AI", encapsulated by our animation model, to navigate the scene using high-level constraints, play against an adversary, and devise a strategy to win a point. To render the resulting state, we use a compositional NeRF representation encapsulated in our synthesis model. To foster future research, we present newly collected, annotated and calibrated Tennis and Minecraft datasets. Our method significantly outperforms existing neural video game simulators in terms of rendering quality and unlocks applications beyond the capabilities of the current state of the art. Our framework, data, and models are available at https://snap-research.github.io/promptable-game-models/.
Authors: Michal Kosinski, Poruz Khambatta, Yilun Wang
Carefully standardized facial images of 591 participants were taken in the laboratory, while controlling for self-presentation, facial expression, head orientation, and image properties. They were presented to human raters and a facial recognition algorithm: both humans (r=.21) and the algorithm (r=.22) could predict participants' scores on a political orientation scale (Cronbach's alpha=.94) decorrelated with age, gender, and ethnicity. These effects are on par with how well job interviews predict job success, or alcohol drives aggressiveness. Algorithm's predictive accuracy was even higher (r=.31) when it leveraged information on participants' age, gender, and ethnicity. Moreover, the associations between facial appearance and political orientation seem to generalize beyond our sample: The predictive model derived from standardized images (while controlling for age, gender, and ethnicity) could predict political orientation (r=.13) from naturalistic images of 3,401 politicians from the U.S., UK, and Canada. The analysis of facial features associated with political orientation revealed that conservatives tended to have larger lower faces. The predictability of political orientation from standardized images has critical implications for privacy, the regulation of facial recognition technology, and understanding the origins and consequences of political orientation.
Authors: Maximilian Bernhard, Niklas Strauß, Matthias Schubert
Change detection in remote sensing imagery is essential for a variety of applications such as urban planning, disaster management, and climate research. However, existing methods for identifying semantically changed areas overlook the availability of semantic information in the form of existing maps describing features of the earth's surface. In this paper, we leverage this information for change detection in bi-temporal images. We show that the simple integration of the additional information via concatenation of latent representations suffices to significantly outperform state-of-the-art change detection methods. Motivated by this observation, we propose the new task of *Conditional Change Detection*, where pre-change semantic information is used as input next to bi-temporal images. To fully exploit the extra information, we propose *MapFormer*, a novel architecture based on a multi-modal feature fusion module that allows for feature processing conditioned on the available semantic information. We further employ a supervised, cross-modal contrastive loss to guide the learning of visual representations. Our approach outperforms existing change detection methods by an absolute 11.7\% and 18.4\% in terms of binary change IoU on DynamicEarthNet and HRSCD, respectively. Furthermore, we demonstrate the robustness of our approach to the quality of the pre-change semantic information and the absence pre-change imagery. The code is available at https://github.com/mxbh/mapformer.
Authors: Polina Karpikova, Radionova Ekaterina, Anastasia Yaschenko, Andrei Spiridonov, Leonid Kostyushko, Riccardo Fabbricatore, Aleksei Ivakhnenko
Generative DNNs are a powerful tool for image synthesis, but they are limited by their computational load. On the other hand, given a trained model and a task, e.g. faces generation within a range of characteristics, the output image quality will be unevenly distributed among images with different characteristics. It follows, that we might restrain the models complexity on some instances, maintaining a high quality. We propose a method for diminishing computations by adding so-called early exit branches to the original architecture, and dynamically switching the computational path depending on how difficult it will be to render the output. We apply our method on two different SOTA models performing generative tasks: generation from a semantic map, and cross-reenactment of face expressions; showing it is able to output images with custom lower-quality thresholds. For a threshold of LPIPS <=0.1, we diminish their computations by up to a half. This is especially relevant for real-time applications such as synthesis of faces, when quality loss needs to be contained, but most of the inputs need fewer computations than the complex instances.
Authors: Dhyey Manish Rajani, Surya Pratap Singh, Rahul Kashyap Swayampakula
We introduce a technique for detecting 3D objects and estimating their position from a single image. Our method is built on top of a similar state-of-the-art technique [1], but with improved accuracy. The approach followed in this research first estimates common 3D properties of an object using a Deep Convolutional Neural Network (DCNN), contrary to other frameworks that only leverage centre-point predictions. We then combine these estimates with geometric constraints provided by a 2D bounding box to produce a complete 3D bounding box. The first output of our network estimates the 3D object orientation using a discrete-continuous loss [1]. The second output predicts the 3D object dimensions with minimal variance. Here we also present our extensions by augmenting light-weight feature extractors and a customized multibin architecture. By combining these estimates with the geometric constraints of the 2D bounding box, we can accurately (or comparatively) determine the 3D object pose better than our baseline [1] on the KITTI 3D detection benchmark [2].
Authors: Bolin Lai, Fiona Ryan, Wenqi Jia, Miao Liu, James M. Rehg
Egocentric gaze anticipation serves as a key building block for the emerging capability of Augmented Reality. Notably, gaze behavior is driven by both visual cues and audio signals during daily activities. Motivated by this observation, we introduce the first model that leverages both the video and audio modalities for egocentric gaze anticipation. Specifically, we propose a Contrastive Spatial-Temporal Separable (CSTS) fusion approach that adopts two modules to separately capture audio-visual correlations in spatial and temporal dimensions, and applies a contrastive loss on the re-weighted audio-visual features from fusion modules for representation learning. We conduct extensive ablation studies and thorough analysis using two egocentric video datasets: Ego4D and Aria, to validate our model design. We also demonstrate our model outperforms prior state-of-the-art methods by at least +1.9% and +1.6%. Moreover, we provide visualizations to show the gaze anticipation results and provide additional insights into audio-visual representation learning.
Authors: Pengcheng Shi, Haozhe Cheng, Xu Han, Yiyang Zhou, Jihua Zhu
Point cloud completion estimates complete shapes from incomplete point clouds to obtain higher-quality point cloud data. Most existing methods only consider global object features, ignoring spatial and semantic information of adjacent points. They cannot distinguish structural information well between different object parts, and the robustness of models is poor. To tackle these challenges, we propose an information interaction-based generative network for point cloud completion ($\mathbf{DualGenerator}$). It contains an adversarial generation path and a variational generation path, which interact with each other and share weights. DualGenerator introduces a local refinement module in generation paths, which captures general structures from partial inputs, and then refines shape details of the point cloud. It promotes completion in the unknown region and makes a distinction between different parts more obvious. Moreover, we design DGStyleGAN to improve the generation quality further. It promotes the robustness of this network combined with fusion analysis of dual-path completion results. Qualitative and quantitative evaluations demonstrate that our method is superior on MVP and Completion3D datasets. The performance will not degrade significantly after adding noise interference or sparse sampling.
Authors: Weifeng Chen, Yatai Ji, Jie Wu, Hefeng Wu, Pan Xie, Jiashi Li, Xin Xia, Xuefeng Xiao, Liang Lin
Recent advancements in diffusion models have unlocked unprecedented abilities in visual creation. However, current text-to-video generation models struggle with the trade-off among movement range, action coherence and object consistency. To mitigate this issue, we present a controllable text-to-video (T2V) diffusion model, called Control-A-Video, capable of maintaining consistency while customizable video synthesis. Based on a pre-trained conditional text-to-image (T2I) diffusion model, our model aims to generate videos conditioned on a sequence of control signals, such as edge or depth maps. For the purpose of improving object consistency, Control-A-Video integrates motion priors and content priors into video generation. We propose two motion-adaptive noise initialization strategies, which are based on pixel residual and optical flow, to introduce motion priors from input videos, producing more coherent videos. Moreover, a first-frame conditioned controller is proposed to generate videos from content priors of the first frame, which facilitates the semantic alignment with text and allows longer video generation in an auto-regressive manner. With the proposed architecture and strategies, our model achieves resource-efficient convergence and generate consistent and coherent videos with fine-grained control. Extensive experiments demonstrate its success in various video generative tasks such as video editing and video style transfer, outperforming previous methods in terms of consistency and quality.
Authors: Yuxin Zhang, Weiming Dong, Fan Tang, Nisha Huang, Haibin Huang, Chongyang Ma, Tong-Yee Lee, Oliver Deussen, Changsheng Xu
Personalizing generative models offers a way to guide image generation with user-provided references. Current personalization methods can invert an object or concept into the textual conditioning space and compose new natural sentences for text-to-image diffusion models. However, representing and editing specific visual attributes such as material, style, and layout remains a challenge, leading to a lack of disentanglement and editability. To address this problem, we propose a novel approach that leverages the step-by-step generation process of diffusion models, which generate images from low to high frequency information, providing a new perspective on representing, generating, and editing images. We develop the Prompt Spectrum Space P*, an expanded textual conditioning space, and a new image representation method called \sysname. ProSpect represents an image as a collection of inverted textual token embeddings encoded from per-stage prompts, where each prompt corresponds to a specific generation stage (i.e., a group of consecutive steps) of the diffusion model. Experimental results demonstrate that P* and ProSpect offer better disentanglement and controllability compared to existing methods. We apply ProSpect in various personalized attribute-aware image generation applications, such as image-guided or text-driven manipulations of materials, style, and layout, achieving previously unattainable results from a single image input without fine-tuning the diffusion models. Our source code is available athttps://github.com/zyxElsa/ProSpect.
Authors: Peter Shaw, Mandar Joshi, James Cohan, Jonathan Berant, Panupong Pasupat, Hexiang Hu, Urvashi Khandelwal, Kenton Lee, Kristina Toutanova
Much of the previous work towards digital agents for graphical user interfaces (GUIs) has relied on text-based representations (derived from HTML or other structured data sources), which are not always readily available. These input representations have been often coupled with custom, task-specific action spaces. This paper focuses on creating agents that interact with the digital world using the same conceptual interface that humans commonly use -- via pixel-based screenshots and a generic action space corresponding to keyboard and mouse actions. Building upon recent progress in pixel-based pretraining, we show, for the first time, that it is possible for such agents to outperform human crowdworkers on the MiniWob++ benchmark of GUI-based instruction following tasks.
Authors: Shaozhe Hao, Kai Han, Shihao Zhao, Kwan-Yee K. Wong
Personalized text-to-image generation using diffusion models has recently emerged and garnered significant interest. This task learns a novel concept (e.g., a unique toy), illustrated in a handful of images, into a generative model that captures fine visual details and generates photorealistic images based on textual embeddings. In this paper, we present ViCo, a novel lightweight plug-and-play method that seamlessly integrates visual condition into personalized text-to-image generation. ViCo stands out for its unique feature of not requiring any fine-tuning of the original diffusion model parameters, thereby facilitating more flexible and scalable model deployment. This key advantage distinguishes ViCo from most existing models that necessitate partial or full diffusion fine-tuning. ViCo incorporates an image attention module that conditions the diffusion process on patch-wise visual semantics, and an attention-based object mask that comes at no extra cost from the attention module. Despite only requiring light parameter training (~6% compared to the diffusion U-Net), ViCo delivers performance that is on par with, or even surpasses, all state-of-the-art models, both qualitatively and quantitatively. This underscores the efficacy of ViCo, making it a highly promising solution for personalized text-to-image generation without the need for diffusion model fine-tuning. Code: https://github.com/haoosz/ViCo
Authors: Luming Tang, Menglin Jia, Qianqian Wang, Cheng Perng Phoo, Bharath Hariharan
Finding correspondences between images is a fundamental problem in computer vision. In this paper, we show that correspondence emerges in image diffusion models without any explicit supervision. We propose a simple strategy to extract this implicit knowledge out of diffusion networks as image features, namely DIffusion FeaTures (DIFT), and use them to establish correspondences between real images. Without any additional fine-tuning or supervision on the task-specific data or annotations, DIFT is able to outperform both weakly-supervised methods and competitive off-the-shelf features in identifying semantic, geometric, and temporal correspondences. Particularly for semantic correspondence, DIFT from Stable Diffusion is able to outperform DINO and OpenCLIP by 19 and 14 accuracy points respectively on the challenging SPair-71k benchmark. It even outperforms the state-of-the-art supervised methods on 9 out of 18 categories while remaining on par for the overall performance. Project page: https://diffusionfeatures.github.io
Authors: Benedict Clark, Rick Wilming, Stefan Haufe
The field of 'explainable' artificial intelligence (XAI) has produced highly cited methods that seek to make the decisions of complex machine learning (ML) methods 'understandable' to humans, for example by attributing 'importance' scores to input features. Yet, a lack of formal underpinning leaves it unclear as to what conclusions can safely be drawn from the results of a given XAI method and has also so far hindered the theoretical verification and empirical validation of XAI methods. This means that challenging non-linear problems, typically solved by deep neural networks, presently lack appropriate remedies. Here, we craft benchmark datasets for three different non-linear classification scenarios, in which the important class-conditional features are known by design, serving as ground truth explanations. Using novel quantitative metrics, we benchmark the explanation performance of a wide set of XAI methods across three deep learning model architectures. We show that popular XAI methods are often unable to significantly outperform random performance baselines and edge detection methods. Moreover, we demonstrate that explanations derived from different model architectures can be vastly different; thus, prone to misinterpretation even under controlled conditions.
Authors: Gabriele Trivigno, Gabriele Berton, Juan Aragon, Barbara Caputo, Carlo Masone
Visual Place recognition is commonly addressed as an image retrieval problem. However, retrieval methods are impractical to scale to large datasets, densely sampled from city-wide maps, since their dimension impact negatively on the inference time. Using approximate nearest neighbour search for retrieval helps to mitigate this issue, at the cost of a performance drop. In this paper we investigate whether we can effectively approach this task as a classification problem, thus bypassing the need for a similarity search. We find that existing classification methods for coarse, planet-wide localization are not suitable for the fine-grained and city-wide setting. This is largely due to how the dataset is split into classes, because these methods are designed to handle a sparse distribution of photos and as such do not consider the visual aliasing problem across neighbouring classes that naturally arises in dense scenarios. Thus, we propose a partitioning scheme that enables a fast and accurate inference, preserving a simple learning procedure, and a novel inference pipeline based on an ensemble of novel classifiers that uses the prototypes learned via an angular margin loss. Our method, Divide&Classify (D&C), enjoys the fast inference of classification solutions and an accuracy competitive with retrieval methods on the fine-grained, city-wide setting. Moreover, we show that D&C can be paired with existing retrieval pipelines to speed up computations by over 20 times while increasing their recall, leading to new state-of-the-art results.
Authors: Yanshu Zhang, Shichong Peng, Alireza Moazeni, Ke Li
Learning accurate and parsimonious point cloud representations of scene surfaces from scratch remains a challenge in 3D representation learning. Existing point-based methods often suffer from the vanishing gradient problem or require a large number of points to accurately model scene geometry and texture. To address these limitations, we propose Proximity Attention Point Rendering (PAPR), a novel method that consists of a point-based scene representation and a differentiable renderer. Our scene representation uses a point cloud where each point is characterized by its spatial position, influence score, and view-independent feature vector. The renderer selects the relevant points for each ray and produces accurate colours using their associated features. PAPR effectively learns point cloud positions to represent the correct scene geometry, even when the initialization drastically differs from the target geometry. Notably, our method captures fine texture details while using only a parsimonious set of points. We also demonstrate four practical applications of our method: zero-shot geometry editing, object manipulation, texture transfer, and exposure control. More results and code are available on our project website at https://zvict.github.io/papr/.
Authors: Bach-Thuan Bui, Dinh-Tuan Tran, Joo-Ho Lee
State-of-the-art visual localization methods mostly rely on complex procedures to match local descriptors and 3D point clouds. However, these procedures can incur significant cost in terms of inference, storage, and updates over time. In this study, we propose a direct learning-based approach that utilizes a simple network named D2S to represent local descriptors and their scene coordinates. Our method is characterized by its simplicity and cost-effectiveness. It solely leverages a single RGB image for localization during the testing phase and only requires a lightweight model to encode a complex sparse scene. The proposed D2S employs a combination of a simple loss function and graph attention to selectively focus on robust descriptors while disregarding areas such as clouds, trees, and several dynamic objects. This selective attention enables D2S to effectively perform a binary-semantic classification for sparse descriptors. Additionally, we propose a new outdoor dataset to evaluate the capabilities of visual localization methods in terms of scene generalization and self-updating from unlabeled observations. Our approach outperforms the state-of-the-art CNN-based methods in scene coordinate regression in indoor and outdoor environments. It demonstrates the ability to generalize beyond training data, including scenarios involving transitions from day to night and adapting to domain shifts, even in the absence of the labeled data sources. The source code, trained models, dataset, and demo videos are available at the following link: https://thpjp.github.io/d2s
Authors: Navid Rajabi, Jana Kosecka
With pre-training of vision-and-language models (VLMs) on large-scale datasets of image-text pairs, several recent works showed that these pre-trained models lack fine-grained understanding, such as the ability to count and recognize verbs, attributes, or relationships. The focus of this work is to study the ability of these models to understand spatial relations. Previously, this has been tackled using image-text matching (e.g., Visual Spatial Reasoning benchmark) or visual question answering (e.g., GQA or VQAv2), both showing poor performance and a large gap compared to human performance. In this work, we use explainability tools to understand the causes of poor performance better and present an alternative fine-grained, compositional approach for ranking spatial clauses. We combine the evidence from grounding noun phrases corresponding to objects and their locations to compute the final rank of the spatial clause. We demonstrate the approach on representative VLMs (such as LXMERT, GPV, and MDETR) and compare and highlight their abilities to reason about spatial relationships.
Authors: Shuman Fang, Zhiwen Lin, Ke Yan, Jie Li, Xianming Lin, Rongrong Ji
The task of Human-Object Interaction (HOI) detection is to detect humans and their interactions with surrounding objects, where transformer-based methods show dominant advances currently. However, these methods ignore the relationship among humans, objects, and interactions: 1) human features are more contributive than object ones to interaction prediction; 2) interactive information disturbs the detection of objects but helps human detection. In this paper, we propose a Human and Object Disentangling Network (HODN) to model the HOI relationships explicitly, where humans and objects are first detected by two disentangling decoders independently and then processed by an interaction decoder. Considering that human features are more contributive to interaction, we propose a Human-Guide Linking method to make sure the interaction decoder focuses on the human-centric regions with human features as the positional embeddings. To handle the opposite influences of interactions on humans and objects, we propose a Stop-Gradient Mechanism to stop interaction gradients from optimizing the object detection but to allow them to optimize the human detection. Our proposed method achieves competitive performance on both the V-COCO and the HICO-Det datasets. It can be combined with existing methods easily for state-of-the-art results.
Authors: Zaber Ibn Abdul Hakim, Rasman Mubtasim Swargo, Muhammad Abdullah Adnan
In this paper, we devise a mechanism for the addition of multi-modal information with an existing pipeline for continuous sign language recognition and translation. In our procedure, we have incorporated optical flow information with RGB images to enrich the features with movement-related information. This work studies the feasibility of such modality inclusion using a cross-modal encoder. The plugin we have used is very lightweight and doesn't need to include a separate feature extractor for the new modality in an end-to-end manner. We have applied the changes in both sign language recognition and translation, improving the result in each case. We have evaluated the performance on the RWTH-PHOENIX-2014 dataset for sign language recognition and the RWTH-PHOENIX-2014T dataset for translation. On the recognition task, our approach reduced the WER by 0.9, and on the translation task, our approach increased most of the BLEU scores by ~0.6 on the test set.
Authors: Anish Bhattacharya, Ratnesh Madaan, Fernando Cladera, Sai Vemprala, Rogerio Bonatti, Kostas Daniilidis, Ashish Kapoor, Vijay Kumar, Nikolai Matni, Jayesh K. Gupta
We present EvDNeRF, a pipeline for generating event data and training an event-based dynamic NeRF, for the purpose of faithfully reconstructing eventstreams on scenes with rigid and non-rigid deformations that may be too fast to capture with a standard camera. Event cameras register asynchronous per-pixel brightness changes at MHz rates with high dynamic range, making them ideal for observing fast motion with almost no motion blur. Neural radiance fields (NeRFs) offer visual-quality geometric-based learnable rendering, but prior work with events has only considered reconstruction of static scenes. Our EvDNeRF can predict eventstreams of dynamic scenes from a static or moving viewpoint between any desired timestamps, thereby allowing it to be used as an event-based simulator for a given scene. We show that by training on varied batch sizes of events, we can improve test-time predictions of events at fine time resolutions, outperforming baselines that pair standard dynamic NeRFs with event generators. We release our simulated and real datasets, as well as code for multi-view event-based data generation and the training and evaluation of EvDNeRF models (https://github.com/anish-bhattacharya/EvDNeRF).
Authors: Lisa Alazraki, Lluis Castrejon, Mostafa Dehghani, Fantine Huot, Jasper Uijlings, Thomas Mensink
This paper studies ensembling in the era of Large Vision-Language Models (LVLMs). Ensembling is a classical method to combine different models to get increased performance. In the recent work on Encyclopedic-VQA the authors examine a wide variety of models to solve their task: from vanilla LVLMs, to models including the caption as extra context, to models augmented with Lens-based retrieval of Wikipedia pages. Intuitively these models are highly complementary, which should make them ideal for ensembling. Indeed, an oracle experiment shows potential gains from 48.8% accuracy (the best single model) all the way up to 67% (best possible ensemble). So it is a trivial exercise to create an ensemble with substantial real gains. Or is it?
Authors: Guanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie, Xiaopeng Zhang, Wei Wei, Wenyu Liu, Qi Tian, Xinggang Wang
Representing and rendering dynamic scenes has been an important but challenging task. Especially, to accurately model complex motions, high efficiency is usually hard to guarantee. To achieve real-time dynamic scene rendering while also enjoying high training and storage efficiency, we propose 4D Gaussian Splatting (4D-GS) as a holistic representation for dynamic scenes rather than applying 3D-GS for each individual frame. In 4D-GS, a novel explicit representation containing both 3D Gaussians and 4D neural voxels is proposed. A decomposed neural voxel encoding algorithm inspired by HexPlane is proposed to efficiently build Gaussian features from 4D neural voxels and then a lightweight MLP is applied to predict Gaussian deformations at novel timestamps. Our 4D-GS method achieves real-time rendering under high resolutions, 82 FPS at an 800$\times$800 resolution on an RTX 3090 GPU while maintaining comparable or better quality than previous state-of-the-art methods. More demos and code are available at https://guanjunwu.github.io/4dgs/.
Authors: Sipeng Zheng, Jiazheng Liu, Yicheng Feng, Zongqing Lu
Recent studies have presented compelling evidence that large language models (LLMs) can equip embodied agents with the self-driven capability to interact with the world, which marks an initial step toward versatile robotics. However, these efforts tend to overlook the visual richness of open worlds, rendering the entire interactive process akin to "a blindfolded text-based game." Consequently, LLM-based agents frequently encounter challenges in intuitively comprehending their surroundings and producing responses that are easy to understand. In this paper, we propose Steve-Eye, an end-to-end trained large multimodal model designed to address this limitation. Steve-Eye integrates the LLM with a visual encoder which enables it to process visual-text inputs and generate multimodal feedback. In addition, we use a semi-automatic strategy to collect an extensive dataset comprising 850K open-world instruction pairs, empowering our model to encompass three essential functions for an agent: multimodal perception, foundational knowledge base, and skill prediction and planning. Lastly, we develop three open-world evaluation benchmarks, then carry out extensive experiments from a wide range of perspectives to validate our model's capability to strategically act and plan. Codes and datasets will be released.
Authors: Muhammad Ferjad Naeem, Yongqin Xian, Xiaohua Zhai, Lukas Hoyer, Luc Van Gool, Federico Tombari
Image-Text pretraining on web-scale image caption datasets has become the default recipe for open vocabulary classification and retrieval models thanks to the success of CLIP and its variants. Several works have also used CLIP features for dense prediction tasks and have shown the emergence of open-set abilities. However, the contrastive objective used by these models only focuses on image-text alignment and does not incentivise image feature learning for dense prediction tasks. In this work, we introduce SILC, a novel framework for vision language pretraining. SILC improves image-text contrastive learning with the simple addition of local-to-global correspondence learning by self-distillation. We show that distilling local image features from an exponential moving average (EMA) teacher model significantly improves model performance on dense predictions tasks like detection and segmentation, while also providing improvements on image-level tasks such as classification and retrieval. SILC models sets a new state of the art for zero-shot classification, few shot classification, image and text retrieval, zero-shot segmentation, and open vocabulary segmentation. We further show that SILC features greatly benefit open vocabulary detection, captioning and visual question answering.
Authors: Binyu Zhao, Wei Zhang, Zhaonian Zou
Collaborative perception enables agents to share complementary perceptual information with nearby agents. This would improve the perception performance and alleviate the issues of single-view perception, such as occlusion and sparsity. Most existing approaches mainly focus on single modality (especially LiDAR), and not fully exploit the superiority of multi-modal perception. We propose a collaborative perception paradigm, BM2CP, which employs LiDAR and camera to achieve efficient multi-modal perception. It utilizes LiDAR-guided modal fusion, cooperative depth generation and modality-guided intermediate fusion to acquire deep interactions among modalities of different agents, Moreover, it is capable to cope with the special case where one of the sensors, same or different type, of any agent is missing. Extensive experiments validate that our approach outperforms the state-of-the-art methods with 50X lower communication volumes in both simulated and real-world autonomous driving scenarios. Our code is available at https://github.com/byzhaoAI/BM2CP.
Authors: Ziyang Yuan, Mingdeng Cao, Xintao Wang, Zhongang Qi, Chun Yuan, Ying Shan
Incorporating a customized object into image generation presents an attractive feature in text-to-image generation. However, existing optimization-based and encoder-based methods are hindered by drawbacks such as time-consuming optimization, insufficient identity preservation, and a prevalent copy-pasting effect. To overcome these limitations, we introduce CustomNet, a novel object customization approach that explicitly incorporates 3D novel view synthesis capabilities into the object customization process. This integration facilitates the adjustment of spatial position relationships and viewpoints, yielding diverse outputs while effectively preserving object identity. Moreover, we introduce delicate designs to enable location control and flexible background control through textual descriptions or specific user-defined images, overcoming the limitations of existing 3D novel view synthesis methods. We further leverage a dataset construction pipeline that can better handle real-world objects and complex backgrounds. Equipped with these designs, our method facilitates zero-shot object customization without test-time optimization, offering simultaneous control over the viewpoints, location, and background. As a result, our CustomNet ensures enhanced identity preservation and generates diverse, harmonious outputs.
Authors: Weixi Wang, Xichen Zhong, Xin Li, Sizhe Li, Xun Ma
Overhead line inspection greatly benefits from defect recognition using visible light imagery. Addressing the limitations of existing feature extraction techniques and the heavy data dependency of deep learning approaches, this paper introduces a novel defect recognition framework. This is built on the Faster RCNN network and complemented by unsupervised semantic segmentation. The approach involves identifying the type and location of the target equipment, utilizing semantic segmentation to differentiate between the device and its backdrop, and finally employing similarity measures and logical rules to categorize the type of defect. Experimental results indicate that this methodology focuses more on the equipment rather than the defects when identifying issues in overhead lines. This leads to a notable enhancement in accuracy and exhibits impressive adaptability. Thus, offering a fresh perspective for automating the inspection of distribution network equipment.
Authors: Yang Zhang
Image-text retrieval is a widely studied topic in the field of computer vision due to the exponential growth of multimedia data, whose core concept is to measure the similarity between images and text. However, most existing retrieval methods heavily rely on cross-attention mechanisms for cross-modal fine-grained alignment, which takes into account excessive irrelevant regions and treats prominent and non-significant words equally, thereby limiting retrieval accuracy. This paper aims to investigate an alignment approach that reduces the involvement of non-significant fragments in images and text while enhancing the alignment of prominent segments. For this purpose, we introduce the Cross-Modal Prominent Fragments Enhancement Aligning Network(CPFEAN), which achieves improved retrieval accuracy by diminishing the participation of irrelevant regions during alignment and relatively increasing the alignment similarity of prominent words. Additionally, we incorporate prior textual information into image regions to reduce misalignment occurrences. In practice, we first design a novel intra-modal fragments relationship reasoning method, and subsequently employ our proposed alignment mechanism to compute the similarity between images and text. Extensive quantitative comparative experiments on MS-COCO and Flickr30K datasets demonstrate that our approach outperforms state-of-the-art methods by about 5% to 10% in the rSum metric.
Authors: Siyi Zhang, Cheng Liu, Xiang Li, Xin Zhai, Zhen Wei, Sizhe Li, Xun Ma
The current trend of automating inspections at substations has sparked a surge in interest in the field of transformer image recognition. However, due to restrictions in the number of parameters in existing models, high-resolution images can't be directly applied, leaving significant room for enhancing recognition accuracy. Addressing this challenge, the paper introduces a novel improvement on deep self-attention networks tailored for this issue. The proposed model comprises four key components: a foundational network, a region proposal network, a module for extracting and segmenting target areas, and a final prediction network. The innovative approach of this paper differentiates itself by decoupling the processes of part localization and recognition, initially using low-resolution images for localization followed by high-resolution images for recognition. Moreover, the deep self-attention network's prediction mechanism uniquely incorporates the semantic context of images, resulting in substantially improved recognition performance. Comparative experiments validate that this method outperforms the two other prevalent target recognition models, offering a groundbreaking perspective for automating electrical equipment inspections.
Authors: Yao Zhu, Yuefeng Chen, Wei Wang, Xiaofeng Mao, Xiu Yan, Yue Wang, Zhigang Li, Wang lu, Jindong Wang, Xiangyang Ji
Learning generalized representations from limited training samples is crucial for applying deep neural networks in low-resource scenarios. Recently, methods based on Contrastive Language-Image Pre-training (CLIP) have exhibited promising performance in few-shot adaptation tasks. To avoid catastrophic forgetting and overfitting caused by few-shot fine-tuning, existing works usually freeze the parameters of CLIP pre-trained on large-scale datasets, overlooking the possibility that some parameters might not be suitable for downstream tasks. To this end, we revisit CLIP's visual encoder with a specific focus on its distinctive attention pooling layer, which performs a spatial weighted-sum of the dense feature maps. Given that dense feature maps contain meaningful semantic information, and different semantics hold varying importance for diverse downstream tasks (such as prioritizing semantics like ears and eyes in pet classification tasks rather than side mirrors), using the same weighted-sum operation for dense features across different few-shot tasks might not be appropriate. Hence, we propose fine-tuning the parameters of the attention pooling layer during the training process to encourage the model to focus on task-specific semantics. In the inference process, we perform residual blending between the features pooled by the fine-tuned and the original attention pooling layers to incorporate both the few-shot knowledge and the pre-trained CLIP's prior knowledge. We term this method as Semantic-Aware FinE-tuning (SAFE). SAFE is effective in enhancing the conventional few-shot CLIP and is compatible with the existing adapter approach (termed SAFE-A).
Authors: Wenxi Zhang, Zhe Li, Weixi Li, Weisi Ma, Xinyi Chen, Sizhe Li
This paper introduces a robust, learning-based method for diagnosing the state of distribution network switchgear, which is crucial for maintaining the power quality for end users. Traditional diagnostic models often rely heavily on expert knowledge and lack robustness. To address this, our method incorporates an expanded feature vector that includes environmental data, temperature readings, switch position, motor operation, insulation conditions, and local discharge information. We tackle the issue of high dimensionality through feature mapping. The method introduces a decision radius to categorize unlabeled samples and updates the model parameters using a combination of supervised and unsupervised loss, along with a consistency regularization function. This approach ensures robust learning even with a limited number of labeled samples. Comparative analysis demonstrates that this method significantly outperforms existing models in both accuracy and robustness.
Authors: Yanwu Xu, Yang Zhao, Zhisheng Xiao, Tingbo Hou
Text-to-image diffusion models have demonstrated remarkable capabilities in transforming textual prompts into coherent images, yet the computational cost of their inference remains a persistent challenge. To address this issue, we present UFOGen, a novel generative model designed for ultra-fast, one-step text-to-image synthesis. In contrast to conventional approaches that focus on improving samplers or employing distillation techniques for diffusion models, UFOGen adopts a hybrid methodology, integrating diffusion models with a GAN objective. Leveraging a newly introduced diffusion-GAN objective and initialization with pre-trained diffusion models, UFOGen excels in efficiently generating high-quality images conditioned on textual descriptions in a single step. Beyond traditional text-to-image generation, UFOGen showcases versatility in applications. Notably, UFOGen stands among the pioneering models enabling one-step text-to-image generation and diverse downstream tasks, presenting a significant advancement in the landscape of efficient generative models.
Authors: Abdul Muqeet, Kyuchul Lee, Bumsoo Kim, Yohan Hong, Hyungrae Lee, Woonggon Kim, KwangHee Lee
Video face re-aging deals with altering the apparent age of a person to the target age in videos. This problem is challenging due to the lack of paired video datasets maintaining temporal consistency in identity and age. Most re-aging methods process each image individually without considering the temporal consistency of videos. While some existing works address the issue of temporal coherence through video facial attribute manipulation in latent space, they often fail to deliver satisfactory performance in age transformation. To tackle the issues, we propose (1) a novel synthetic video dataset that features subjects across a diverse range of age groups; (2) a baseline architecture designed to validate the effectiveness of our proposed dataset, and (3) the development of three novel metrics tailored explicitly for evaluating the temporal consistency of video re-aging techniques. Our comprehensive experiments on public datasets, such as VFHQ and CelebV-HQ, show that our method outperforms the existing approaches in terms of both age transformation and temporal consistency.
Authors: Xiangyu Xiong, Yue Sun, Xiaohong Liu, Chan-Tong Lam, Tong Tong, Hao Chen, Qinquan Gao, Wei Ke, Tao Tan
Although current data augmentation methods are successful to alleviate the data insufficiency, conventional augmentation are primarily intra-domain while advanced generative adversarial networks (GANs) generate images remaining uncertain, particularly in small-scale datasets. In this paper, we propose a parameterized GAN (ParaGAN) that effectively controls the changes of synthetic samples among domains and highlights the attention regions for downstream classification. Specifically, ParaGAN incorporates projection distance parameters in cyclic projection and projects the source images to the decision boundary to obtain the class-difference maps. Our experiments show that ParaGAN can consistently outperform the existing augmentation methods with explainable classification on two small-scale medical datasets.
Authors: Meilong Xu, Xiaoling Hu, Saumya Gupta, Shahira Abousamra, Chao Chen
In computational pathology, segmenting densely distributed objects like glands and nuclei is crucial for downstream analysis. To alleviate the burden of obtaining pixel-wise annotations, semi-supervised learning methods learn from large amounts of unlabeled data. Nevertheless, existing semi-supervised methods overlook the topological information hidden in the unlabeled images and are thus prone to topological errors, e.g., missing or incorrectly merged/separated glands or nuclei. To address this issue, we propose TopoSemiSeg, the first semi-supervised method that learns the topological representation from unlabeled data. In particular, we propose a topology-aware teacher-student approach in which the teacher and student networks learn shared topological representations. To achieve this, we introduce topological consistency loss, which contains signal consistency and noise removal losses to ensure the learned representation is robust and focuses on true topological signals. Extensive experiments on public pathology image datasets show the superiority of our method, especially on topology-wise evaluation metrics. Code is available at https://github.com/Melon-Xu/TopoSemiSeg.
Authors: Junyi Ma, Xieyuanli Chen, Jiawei Huang, Jingyi Xu, Zhen Luo, Jintao Xu, Weihao Gu, Rui Ai, Hesheng Wang
Understanding how the surrounding environment changes is crucial for performing downstream tasks safely and reliably in autonomous driving applications. Recent occupancy estimation techniques using only camera images as input can provide dense occupancy representations of large-scale scenes based on the current observation. However, they are mostly limited to representing the current 3D space and do not consider the future state of surrounding objects along the time axis. To extend camera-only occupancy estimation into spatiotemporal prediction, we propose Cam4DOcc, a new benchmark for camera-only 4D occupancy forecasting, evaluating the surrounding scene changes in a near future. We build our benchmark based on multiple publicly available datasets, including nuScenes, nuScenes-Occupancy, and Lyft-Level5, which provides sequential occupancy states of general movable and static objects, as well as their 3D backward centripetal flow. To establish this benchmark for future research with comprehensive comparisons, we introduce four baseline types from diverse camera-based perception and prediction implementations, including a static-world occupancy model, voxelization of point cloud prediction, 2D-3D instance-based prediction, and our proposed novel end-to-end 4D occupancy forecasting network. Furthermore, the standardized evaluation protocol for preset multiple tasks is also provided to compare the performance of all the proposed baselines on present and future occupancy estimation with respect to objects of interest in autonomous driving scenarios. The dataset and our implementation of all four baselines in the proposed Cam4DOcc benchmark will be released here: https://github.com/haomo-ai/Cam4DOcc.
Authors: Eric Hedlin, Gopal Sharma, Shweta Mahajan, Xingzhe He, Hossam Isack, Abhishek Kar Helge Rhodin, Andrea Tagliasacchi, Kwang Moo Yi
Unsupervised learning of keypoints and landmarks has seen significant progress with the help of modern neural network architectures, but performance is yet to match the supervised counterpart, making their practicability questionable. We leverage the emergent knowledge within text-to-image diffusion models, towards more robust unsupervised keypoints. Our core idea is to find text embeddings that would cause the generative model to consistently attend to compact regions in images (i.e. keypoints). To do so, we simply optimize the text embedding such that the cross-attention maps within the denoising network are localized as Gaussians with small standard deviations. We validate our performance on multiple datasets: the CelebA, CUB-200-2011, Tai-Chi-HD, DeepFashion, and Human3.6m datasets. We achieve significantly improved accuracy, sometimes even outperforming supervised ones, particularly for data that is non-aligned and less curated. Our code is publicly available and can be found through our project page: https://ubc-vision.github.io/StableKeypoints/
Authors: Haokun Chen, Xu Yang, Yuhang Huang, Zihan Wu, Jing Wang, Xin Geng
After pre-training by generating the next word conditional on previous words, the Language Model (LM) acquires the ability of In-Context Learning (ICL) that can learn a new task conditional on the context of the given in-context examples (ICEs). Similarly, visually-conditioned Language Modelling is also used to train Vision-Language Models (VLMs) with ICL ability. However, such VLMs typically exhibit weaker classification abilities compared to contrastive learning-based models like CLIP, since the Language Modelling objective does not directly contrast whether an object is paired with a text. To improve the ICL of classification, using more ICEs to provide more knowledge is a straightforward way. However, this may largely increase the selection time, and more importantly, the inclusion of additional in-context images tends to extend the length of the in-context sequence beyond the processing capacity of a VLM. To alleviate these limitations, we propose to manipulate the label space of each ICE to increase its knowledge density, allowing for fewer ICEs to convey as much information as a larger set would. Specifically, we propose two strategies which are Label Distribution Enhancement and Visual Descriptions Enhancement to improve In-context classification performance on diverse datasets, including the classic ImageNet and more fine-grained datasets like CUB-200. Specifically, using our approach on ImageNet, we increase accuracy from 74.70\% in a 4-shot setting to 76.21\% with just 2 shots. surpassing CLIP by 0.67\%. On CUB-200, our method raises 1-shot accuracy from 48.86\% to 69.05\%, 12.15\% higher than CLIP. The code is given in https://anonymous.4open.science/r/MLS_ICC.
Authors: Jaime Corsetti, Davide Boscaini, Changjae Oh, Andrea Cavallaro, Fabio Poiesi
We introduce the new setting of open-vocabulary object 6D pose estimation, in which a textual prompt is used to specify the object of interest. In contrast to existing approaches, in our setting (i) the object of interest is specified solely through the textual prompt, (ii) no object model (e.g. CAD or video sequence) is required at inference, (iii) the object is imaged from two different viewpoints of two different scenes, and (iv) the object was not observed during the training phase. To operate in this setting, we introduce a novel approach that leverages a Vision-Language Model to segment the object of interest from two distinct scenes and to estimate its relative 6D pose. The key of our approach is a carefully devised strategy to fuse object-level information provided by the prompt with local image features, resulting in a feature space that can generalize to novel concepts. We validate our approach on a new benchmark based on two popular datasets, REAL275 and Toyota-Light, which collectively encompass 39 object instances appearing in four thousand image pairs. The results demonstrate that our approach outperforms both a well-established hand-crafted method and a recent deep learning-based baseline in estimating the relative 6D pose of objects in different scenes. Project page: https://jcorsetti.github.io/oryon/.
Authors: Guillaume Le Moing, Jean Ponce, Cordelia Schmid
Recent approaches to point tracking are able to recover the trajectory of any scene point through a large portion of a video despite the presence of occlusions. They are, however, too slow in practice to track every point observed in a single frame in a reasonable amount of time. This paper introduces DOT, a novel, simple and efficient method for solving this problem. It first extracts a small set of tracks from key regions at motion boundaries using an off-the-shelf point tracking algorithm. Given source and target frames, DOT then computes rough initial estimates of a dense flow field and visibility mask through nearest-neighbor interpolation, before refining them using a learnable optical flow estimator that explicitly handles occlusions and can be trained on synthetic data with ground-truth correspondences. We show that DOT is significantly more accurate than current optical flow techniques, outperforms sophisticated "universal" trackers like OmniMotion, and is on par with, or better than, the best point tracking algorithms like CoTracker while being at least two orders of magnitude faster. Quantitative and qualitative experiments with synthetic and real videos validate the promise of the proposed approach. Code, data, and videos showcasing the capabilities of our approach are available in the project webpage: https://16lemoing.github.io/dot .
Authors: Yong Liu, Cairong Zhang, Yitong Wang, Jiahao Wang, Yujiu Yang, Yansong Tang
This paper aims to achieve universal segmentation of arbitrary semantic level. Despite significant progress in recent years, specialist segmentation approaches are limited to specific tasks and data distribution. Retraining a new model for adaptation to new scenarios or settings takes expensive computation and time cost, which raises the demand for versatile and universal segmentation model that can cater to various granularity. Although some attempts have been made for unifying different segmentation tasks or generalization to various scenarios, limitations in the definition of paradigms and input-output spaces make it difficult for them to achieve accurate understanding of content at arbitrary granularity. To this end, we present UniLSeg, a universal segmentation model that can perform segmentation at any semantic level with the guidance of language instructions. For training UniLSeg, we reorganize a group of tasks from original diverse distributions into a unified data format, where images with texts describing segmentation targets as input and corresponding masks are output. Combined with a automatic annotation engine for utilizing numerous unlabeled data, UniLSeg achieves excellent performance on various tasks and settings, surpassing both specialist and unified segmentation models.
Authors: Xusen Sun, Longhao Zhang, Hao Zhu, Peng Zhang, Bang Zhang, Xinya Ji, Kangneng Zhou, Daiheng Gao, Liefeng Bo, Xun Cao
Audio-driven talking head generation has drawn much attention in recent years, and many efforts have been made in lip-sync, expressive facial expressions, natural head pose generation, and high video quality. However, no model has yet led or tied on all these metrics due to the one-to-many mapping between audio and motion. In this paper, we propose VividTalk, a two-stage generic framework that supports generating high-visual quality talking head videos with all the above properties. Specifically, in the first stage, we map the audio to mesh by learning two motions, including non-rigid expression motion and rigid head motion. For expression motion, both blendshape and vertex are adopted as the intermediate representation to maximize the representation ability of the model. For natural head motion, a novel learnable head pose codebook with a two-phase training mechanism is proposed. In the second stage, we proposed a dual branch motion-vae and a generator to transform the meshes into dense motion and synthesize high-quality video frame-by-frame. Extensive experiments show that the proposed VividTalk can generate high-visual quality talking head videos with lip-sync and realistic enhanced by a large margin, and outperforms previous state-of-the-art works in objective and subjective comparisons.
Authors: Philipp Rigoll, Jacob Langner, Eric Sax
Huge image data sets are the fundament for the development of the perception of automated driving systems. A large number of images is necessary to train robust neural networks that can cope with diverse situations. A sufficiently large data set contains challenging situations and objects. For testing the resulting functions, it is necessary that these situations and objects can be found and extracted from the data set. While it is relatively easy to record a large amount of unlabeled data, it is far more difficult to find demanding situations and objects. However, during the development of perception systems, it must be possible to access challenging data without having to perform lengthy and time-consuming annotations. A developer must therefore be able to search dynamically for specific situations and objects in a data set. Thus, we designed a method which is based on state-of-the-art neural networks to search for objects with certain properties within an image. For the ease of use, the query of this search is described using natural language. To determine the time savings and performance gains, we evaluated our method qualitatively and quantitatively on automotive data sets.
Authors: Karran Pandey, Paul Guerrero, Matheus Gadelha, Yannick Hold-Geoffroy, Karan Singh, Niloy Mitra
Diffusion Handles is a novel approach to enabling 3D object edits on diffusion images. We accomplish these edits using existing pre-trained diffusion models, and 2D image depth estimation, without any fine-tuning or 3D object retrieval. The edited results remain plausible, photo-real, and preserve object identity. Diffusion Handles address a critically missing facet of generative image based creative design, and significantly advance the state-of-the-art in generative image editing. Our key insight is to lift diffusion activations for an object to 3D using a proxy depth, 3D-transform the depth and associated activations, and project them back to image space. The diffusion process applied to the manipulated activations with identity control, produces plausible edited images showing complex 3D occlusion and lighting effects. We evaluate Diffusion Handles: quantitatively, on a large synthetic data benchmark; and qualitatively by a user study, showing our output to be more plausible, and better than prior art at both, 3D editing and identity control. Project Webpage: https://diffusionhandles.github.io/
Authors: Fan Yang, Tianyi Chen, Xiaosheng He, Zhongang Cai, Lei Yang, Si Wu, Guosheng Lin
Editable 3D-aware generation, which supports user-interacted editing, has witnessed rapid development recently. However, existing editable 3D GANs either fail to achieve high-accuracy local editing or suffer from huge computational costs. We propose AttriHuman-3D, an editable 3D human generation model, which address the aforementioned problems with attribute decomposition and indexing. The core idea of the proposed model is to generate all attributes (e.g. human body, hair, clothes and so on) in an overall attribute space with six feature planes, which are then decomposed and manipulated with different attribute indexes. To precisely extract features of different attributes from the generated feature planes, we propose a novel attribute indexing method as well as an orthogonal projection regularization to enhance the disentanglement. We also introduce a hyper-latent training strategy and an attribute-specific sampling strategy to avoid style entanglement and misleading punishment from the discriminator. Our method allows users to interactively edit selected attributes in the generated 3D human avatars while keeping others fixed. Both qualitative and quantitative experiments demonstrate that our model provides a strong disentanglement between different attributes, allows fine-grained image editing and generates high-quality 3D human avatars.
Authors: Lingmin Ran, Xiaodong Cun, Jia-Wei Liu, Rui Zhao, Song Zijie, Xintao Wang, Jussi Keppo, Mike Zheng Shou
We introduce X-Adapter, a universal upgrader to enable the pretrained plug-and-play modules (e.g., ControlNet, LoRA) to work directly with the upgraded text-to-image diffusion model (e.g., SDXL) without further retraining. We achieve this goal by training an additional network to control the frozen upgraded model with the new text-image data pairs. In detail, X-Adapter keeps a frozen copy of the old model to preserve the connectors of different plugins. Additionally, X-Adapter adds trainable mapping layers that bridge the decoders from models of different versions for feature remapping. The remapped features will be used as guidance for the upgraded model. To enhance the guidance ability of X-Adapter, we employ a null-text training strategy for the upgraded model. After training, we also introduce a two-stage denoising strategy to align the initial latents of X-Adapter and the upgraded model. Thanks to our strategies, X-Adapter demonstrates universal compatibility with various plugins and also enables plugins of different versions to work together, thereby expanding the functionalities of diffusion community. To verify the effectiveness of the proposed method, we conduct extensive experiments and the results show that X-Adapter may facilitate wider application in the upgraded foundational diffusion model.
Authors: Arun Reddy, William Paul, Corban Rivera, Ketul Shah, Celso M. de Melo, Rama Chellappa
In this work, we tackle the problem of unsupervised domain adaptation (UDA) for video action recognition. Our approach, which we call UNITE, uses an image teacher model to adapt a video student model to the target domain. UNITE first employs self-supervised pre-training to promote discriminative feature learning on target domain videos using a teacher-guided masked distillation objective. We then perform self-training on masked target data, using the video student model and image teacher model together to generate improved pseudolabels for unlabeled target videos. Our self-training process successfully leverages the strengths of both models to achieve strong transfer performance across domains. We evaluate our approach on multiple video domain adaptation benchmarks and observe significant improvements upon previously reported results.
Authors: Seungju Cho, Hongsin Lee, Changick Kim
Adversarial training integrates adversarial examples during model training to enhance robustness. However, its application in fixed dataset settings differs from real-world dynamics, where data accumulates incrementally. In this study, we investigate Adversarially Robust Class Incremental Learning (ARCIL), a method that combines adversarial robustness with incremental learning. We observe that combining incremental learning with naive adversarial training easily leads to a loss of robustness. We discover that this is attributed to the disappearance of the flatness of the loss function, a characteristic of adversarial training. To address this issue, we propose the Flatness Preserving Distillation (FPD) loss that leverages the output difference between adversarial and clean examples. Additionally, we introduce the Logit Adjustment Distillation (LAD) loss, which adapts the model's knowledge to perform well on new tasks. Experimental results demonstrate the superiority of our method over approaches that apply adversarial training to existing incremental learning methods, which provides a strong baseline for incremental learning on adversarial robustness in the future. Our method achieves AutoAttack accuracy that is 5.99\%p, 5.27\%p, and 3.90\%p higher on average than the baseline on split CIFAR-10, CIFAR-100, and Tiny ImageNet, respectively. The code will be made available.
Authors: Chao Chen, Tian Zhou, Yanjun Zhao, Hui Liu, Liang Sun, Rong Jin
Spatiotemporal forecasting tasks, such as weather forecasting and traffic prediction, offer significant societal benefits. These tasks can be effectively approached as image forecasting problems using computer vision models. Vector quantization (VQ) is a well-known method for discrete representation that improves the latent space, leading to enhanced generalization and transfer learning capabilities. One of the main challenges in using VQ for spatiotemporal forecasting is how to balance between keeping enough details and removing noises from the original patterns for better generalization. We address this challenge by developing sparse vector quantization, or {\bf SVQ} for short, that leverages sparse regression to make better trade-off between the two objectives. The main innovation of this work is to approximate sparse regression by a two-layer MLP and a randomly fixed or learnable matrix, dramatically improving its computational efficiency. Through experiments conducted on diverse datasets in multiple fields including weather forecasting, traffic flow prediction, and video forecasting, we unequivocally demonstrate that our proposed method consistently enhances the performance of base models and achieves state-of-the-art results across all benchmarks.
Authors: Yuheng Jiang, Zhehao Shen, Penghao Wang, Zhuo Su, Yu Hong, Yingliang Zhang, Jingyi Yu, Lan Xu
We have recently seen tremendous progress in photo-real human modeling and rendering. Yet, efficiently rendering realistic human performance and integrating it into the rasterization pipeline remains challenging. In this paper, we present HiFi4G, an explicit and compact Gaussian-based approach for high-fidelity human performance rendering from dense footage. Our core intuition is to marry the 3D Gaussian representation with non-rigid tracking, achieving a compact and compression-friendly representation. We first propose a dual-graph mechanism to obtain motion priors, with a coarse deformation graph for effective initialization and a fine-grained Gaussian graph to enforce subsequent constraints. Then, we utilize a 4D Gaussian optimization scheme with adaptive spatial-temporal regularizers to effectively balance the non-rigid prior and Gaussian updating. We also present a companion compression scheme with residual compensation for immersive experiences on various platforms. It achieves a substantial compression rate of approximately 25 times, with less than 2MB of storage per frame. Extensive experiments demonstrate the effectiveness of our approach, which significantly outperforms existing approaches in terms of optimization speed, rendering quality, and storage overhead.
Authors: Junhao Zhuang, Yanhong Zeng, Wenran Liu, Chun Yuan, Kai Chen
Achieving high-quality versatile image inpainting, where user-specified regions are filled with plausible content according to user intent, presents a significant challenge. Existing methods face difficulties in simultaneously addressing context-aware image inpainting and text-guided object inpainting due to the distinct optimal training strategies required. To overcome this challenge, we introduce PowerPaint, the first high-quality and versatile inpainting model that excels in both tasks. First, we introduce learnable task prompts along with tailored fine-tuning strategies to guide the model's focus on different inpainting targets explicitly. This enables PowerPaint to accomplish various inpainting tasks by utilizing different task prompts, resulting in state-of-the-art performance. Second, we demonstrate the versatility of the task prompt in PowerPaint by showcasing its effectiveness as a negative prompt for object removal. Additionally, we leverage prompt interpolation techniques to enable controllable shape-guided object inpainting. Finally, we extensively evaluate PowerPaint on various inpainting benchmarks to demonstrate its superior performance for versatile image inpainting. We release our codes and models on our project page: https://powerpaint.github.io/.
Authors: Chris Careaga, S. Mahdi H. Miangoleh, Yağız Aksoy
Despite significant advancements in network-based image harmonization techniques, there still exists a domain disparity between typical training pairs and real-world composites encountered during inference. Most existing methods are trained to reverse global edits made on segmented image regions, which fail to accurately capture the lighting inconsistencies between the foreground and background found in composited images. In this work, we introduce a self-supervised illumination harmonization approach formulated in the intrinsic image domain. First, we estimate a simple global lighting model from mid-level vision representations to generate a rough shading for the foreground region. A network then refines this inferred shading to generate a harmonious re-shading that aligns with the background scene. In order to match the color appearance of the foreground and background, we utilize ideas from prior harmonization approaches to perform parameterized image edits in the albedo domain. To validate the effectiveness of our approach, we present results from challenging real-world composites and conduct a user study to objectively measure the enhanced realism achieved compared to state-of-the-art harmonization methods.