Authors: Zixuan Huang, Stefan Stojanov, Anh Thai, Varun Jampani, James M. Rehg
We study the problem of single-image zero-shot 3D shape reconstruction. Recent works learn zero-shot shape reconstruction through generative modeling of 3D assets, but these models are computationally expensive at train and inference time. In contrast, the traditional approach to this problem is regression-based, where deterministic models are trained to directly regress the object shape. Such regression methods possess much higher computational efficiency than generative methods. This raises a natural question: is generative modeling necessary for high performance, or conversely, are regression-based approaches still competitive? To answer this, we design a strong regression-based model, called ZeroShape, based on the converging findings in this field and a novel insight. We also curate a large real-world evaluation benchmark, with objects from three different real-world 3D datasets. This evaluation benchmark is more diverse and an order of magnitude larger than what prior works use to quantitatively evaluate their models, aiming at reducing the evaluation variance in our field. We show that ZeroShape not only achieves superior performance over state-of-the-art methods, but also demonstrates significantly higher computational and data efficiency.
Authors: Chongjun Tu, Peng Ye, Weihao Lin, Hancheng Ye, Chong Yu, Tao Chen, Baopu Li, Wanli Ouyang
Improving the efficiency of Neural Architecture Search (NAS) is a challenging but significant task that has received much attention. Previous works mainly adopted the Differentiable Architecture Search (DARTS) and improved its search strategies or modules to enhance search efficiency. Recently, some methods have started considering data reduction for speedup, but they are not tightly coupled with the architecture search process, resulting in sub-optimal performance. To this end, this work pioneers an exploration into the critical role of dataset characteristics for DARTS bi-level optimization, and then proposes a novel Bi-level Data Pruning (BDP) paradigm that targets the weights and architecture levels of DARTS to enhance efficiency from a data perspective. Specifically, we introduce a new progressive data pruning strategy that utilizes supernet prediction dynamics as the metric, to gradually prune unsuitable samples for DARTS during the search. An effective automatic class balance constraint is also integrated into BDP, to suppress potential class imbalances resulting from data-efficient algorithms. Comprehensive evaluations on the NAS-Bench-201 search space, DARTS search space, and MobileNet-like search space validate that BDP reduces search costs by over 50% while achieving superior performance when applied to baseline DARTS. Besides, we demonstrate that BDP can harmoniously integrate with advanced DARTS variants, like PC-DARTS and \b{eta}-DARTS, offering an approximately 2 times speedup with minimal performance compromises.
Authors: Jung-Ho Hong, Woo-Jeoung Nam, Kyu-Sung Jeon, Seong-Whan Lee
Revealing the transparency of Deep Neural Networks (DNNs) has been widely studied to describe the decision mechanisms of network inner structures. In this paper, we propose a novel post-hoc framework, Unfold and Conquer Attribution Guidance (UCAG), which enhances the explainability of the network decision by spatially scrutinizing the input features with respect to the model confidence. Addressing the phenomenon of missing detailed descriptions, UCAG sequentially complies with the confidence of slices of the image, leading to providing an abundant and clear interpretation. Therefore, it is possible to enhance the representation ability of explanation by preserving the detailed descriptions of assistant input features, which are commonly overwhelmed by the main meaningful regions. We conduct numerous evaluations to validate the performance in several metrics: i) deletion and insertion, ii) (energy-based) pointing games, and iii) positive and negative density maps. Experimental results, including qualitative comparisons, demonstrate that our method outperforms the existing methods with the nature of clear and detailed explanations and applicability.
Authors: Wei Feng, Xin Wang, Hong Chen, Zeyang Zhang, Zihan Song, Yuwei Zhou, Wenwu Zhu
Recently, researchers have attempted to investigate the capability of LLMs in handling videos and proposed several video LLM models. However, the ability of LLMs to handle video grounding (VG), which is an important time-related video task requiring the model to precisely locate the start and end timestamps of temporal moments in videos that match the given textual queries, still remains unclear and unexplored in literature. To fill the gap, in this paper, we propose the LLM4VG benchmark, which systematically evaluates the performance of different LLMs on video grounding tasks. Based on our proposed LLM4VG, we design extensive experiments to examine two groups of video LLM models on video grounding: (i) the video LLMs trained on the text-video pairs (denoted as VidLLM), and (ii) the LLMs combined with pretrained visual description models such as the video/image captioning model. We propose prompt methods to integrate the instruction of VG and description from different kinds of generators, including caption-based generators for direct visual description and VQA-based generators for information enhancement. We also provide comprehensive comparisons of various VidLLMs and explore the influence of different choices of visual models, LLMs, prompt designs, etc, as well. Our experimental evaluations lead to two conclusions: (i) the existing VidLLMs are still far away from achieving satisfactory video grounding performance, and more time-related video tasks should be included to further fine-tune these models, and (ii) the combination of LLMs and visual models shows preliminary abilities for video grounding with considerable potential for improvement by resorting to more reliable models and further guidance of prompt instructions.
Authors: Chunyang Cheng, Tianyang Xu, Xiao-Jun Wu, Hui Li, Xi Li, Zhangyong Tang, Josef Kittler
Advanced image fusion methods are devoted to generating the fusion results by aggregating the complementary information conveyed by the source images. However, the difference in the source-specific manifestation of the imaged scene content makes it difficult to design a robust and controllable fusion process. We argue that this issue can be alleviated with the help of higher-level semantics, conveyed by the text modality, which should enable us to generate fused images for different purposes, such as visualisation and downstream tasks, in a controllable way. This is achieved by exploiting a vision-and-language model to build a coarse-to-fine association mechanism between the text and image signals. With the guidance of the association maps, an affine fusion unit is embedded in the transformer network to fuse the text and vision modalities at the feature level. As another ingredient of this work, we propose the use of textual attention to adapt image quality assessment to the fusion task. To facilitate the implementation of the proposed text-guided fusion paradigm, and its adoption by the wider research community, we release a text-annotated image fusion dataset IVT. Extensive experiments demonstrate that our approach (TextFusion) consistently outperforms traditional appearance-based fusion methods. Our code and dataset will be publicly available on the project homepage.
Authors: Brian Nlong Zhao, Yuhang Xiao, Jiashu Xu, Xinyang Jiang, Yifan Yang, Dongsheng Li, Laurent Itti, Vibhav Vineet, Yunhao Ge
The popularization of Text-to-Image (T2I) diffusion models enables the generation of high-quality images from text descriptions. However, generating diverse customized images with reference visual attributes remains challenging. This work focuses on personalizing T2I diffusion models at a more abstract concept or category level, adapting commonalities from a set of reference images while creating new instances with sufficient variations. We introduce a solution that allows a pretrained T2I diffusion model to learn a set of soft prompts, enabling the generation of novel images by sampling prompts from the learned distribution. These prompts offer text-guided editing capabilities and additional flexibility in controlling variation and mixing between multiple distributions. We also show the adaptability of the learned prompt distribution to other tasks, such as text-to-3D. Finally we demonstrate effectiveness of our approach through quantitative analysis including automatic evaluation and human assessment. Project website: https://briannlongzhao.github.io/DreamDistribution
Authors: Haobo Lu, Xin Liu, Kun He
Deep Neural Networks (DNNs) are widely acknowledged to be susceptible to adversarial examples, wherein imperceptible perturbations are added to clean examples through diverse input transformation attacks. However, these methods originally designed for non-targeted attacks exhibit low success rates in targeted attacks. Recent targeted adversarial attacks mainly pay attention to gradient optimization, attempting to find the suitable perturbation direction. However, few of them are dedicated to input transformation.In this work, we observe a positive correlation between the logit/probability of the target class and diverse input transformation methods in targeted attacks. To this end, we propose a novel targeted adversarial attack called AutoAugment Input Transformation (AAIT). Instead of relying on hand-made strategies, AAIT searches for the optimal transformation policy from a transformation space comprising various operations. Then, AAIT crafts adversarial examples using the found optimal transformation policy to boost the adversarial transferability in targeted attacks. Extensive experiments conducted on CIFAR-10 and ImageNet-Compatible datasets demonstrate that the proposed AAIT surpasses other transfer-based targeted attacks significantly.
Authors: Nina Weng, Paraskevas Pegios, Aasa Feragen, Eike Petersen, Siavash Bigdeli
Shortcut learning is when a model -- e.g. a cardiac disease classifier -- exploits correlations between the target label and a spurious shortcut feature, e.g. a pacemaker, to predict the target label based on the shortcut rather than real discriminative features. This is common in medical imaging, where treatment and clinical annotations correlate with disease labels, making them easy shortcuts to predict disease. We propose a novel detection and quantification of the impact of potential shortcut features via a fast diffusion-based counterfactual image generation that can synthetically remove or add shortcuts. Via a novel inpainting-based modification we spatially limit the changes made with no extra inference step, encouraging the removal of spatially constrained shortcut features while ensuring that the shortcut-free counterfactuals preserve their remaining image features to a high degree. Using these, we assess how shortcut features influence model predictions.
This is enabled by our second contribution: An efficient diffusion-based counterfactual explanation method with significant inference speed-up at comparable image quality as state-of-the-art. We confirm this on two large chest X-ray datasets, a skin lesion dataset, and CelebA.
Authors: Yiqi Lin, Conghui He, Alex Jinpeng Wang, Bin Wang, Weijia Li, Mike Zheng Shou
Despite CLIP being the foundation model in numerous vision-language applications, the CLIP suffers from a severe text spotting bias. Such bias causes CLIP models to `Parrot' the visual text embedded within images while disregarding the authentic visual semantics. We uncover that in the most popular image-text dataset LAION-2B, the captions also densely parrot (spell) the text embedded in images. Our analysis shows that around \textbf{50\%} of images are embedded with visual text content, and \textbf{90\%} of their captions more or less parrot the visual text. Based on such observation, we thoroughly inspect the different release d versions of CLIP models and verify that the visual text is the dominant factor in measuring the LAION-style image-text similarity for these models. To examine whether these parrot captions shape the text spotting bias, we train a series of CLIP models with LAION subsets curated by different parrot-caption-oriented criteria. We show that training with parrot captions easily shapes such bias but harms the expected visual-language representation learning in CLIP models. This suggests that it is urgent to revisit either the design of CLIP-like models or the existing image-text dataset curation pipeline built on CLIP score filtering.
Authors: Jitesh Jain, Jianwei Yang, Humphrey Shi
Humans possess the remarkable skill of Visual Perception, the ability to see and understand the seen, helping them make sense of the visual world and, in turn, reason. Multimodal Large Language Models (MLLM) have recently achieved impressive performance on vision-language tasks ranging from visual question-answering and image captioning to visual reasoning and image generation. However, when prompted to identify or count (perceive) the entities in a given image, existing MLLM systems fail. Working towards developing an accurate MLLM system for perception and reasoning, we propose using Versatile vision enCoders (VCoder) as perception eyes for Multimodal LLMs. We feed the VCoder with perception modalities such as segmentation or depth maps, improving the MLLM's perception abilities. Secondly, we leverage the images from COCO and outputs from off-the-shelf vision perception models to create our COCO Segmentation Text (COST) dataset for training and evaluating MLLMs on the object perception task. Thirdly, we introduce metrics to assess the object perception abilities in MLLMs on our COST dataset. Lastly, we provide extensive experimental evidence proving the VCoder's improved object-level perception skills over existing Multimodal LLMs, including GPT-4V. We open-source our dataset, code, and models to promote research. We open-source our code at https://github.com/SHI-Labs/VCoder
Authors: Ilya Chugunov, David Shustin, Ruyu Yan, Chenyang Lei, Felix Heide
Each photo in an image burst can be considered a sample of a complex 3D scene: the product of parallax, diffuse and specular materials, scene motion, and illuminant variation. While decomposing all of these effects from a stack of misaligned images is a highly ill-conditioned task, the conventional align-and-merge burst pipeline takes the other extreme: blending them into a single image. In this work, we propose a versatile intermediate representation: a two-layer alpha-composited image plus flow model constructed with neural spline fields -- networks trained to map input coordinates to spline control points. Our method is able to, during test-time optimization, jointly fuse a burst image capture into one high-resolution reconstruction and decompose it into transmission and obstruction layers. Then, by discarding the obstruction layer, we can perform a range of tasks including seeing through occlusions, reflection suppression, and shadow removal. Validated on complex synthetic and in-the-wild captures we find that, with no post-processing steps or learned priors, our generalizable model is able to outperform existing dedicated single-image and multi-view obstruction removal approaches.
Authors: Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Zhong Muyan, Qinglong Zhang, Xizhou Zhu, Lewei Lu, Bin Li, Ping Luo, Tong Lu, Yu Qiao, Jifeng Dai
The exponential growth of large language models (LLMs) has opened up numerous possibilities for multi-modal AGI systems. However, the progress in vision and vision-language foundation models, which are also critical elements of multi-modal AGI, has not kept pace with LLMs. In this work, we design a large-scale vision-language foundation model (InternVL), which scales up the vision foundation model to 6 billion parameters and progressively aligns it with the large language model, using web-scale image-text data from various sources. This model can be broadly applied to and achieve state-of-the-art performance on visual perception tasks such as image-level or pixel-level recognition, vision-language tasks such as zero-shot image/video classification, zero-shot image/video-text retrieval, and link with LLMs to create multi-modal dialogue systems. We hope that our research could contribute to the development of multi-modal large models. Code and models are available at https://github.com/OpenGVLab/InternVL.
Authors: Tzofi Klinghoffer, Xiaoyu Xiang, Siddharth Somasundaram, Yuchen Fan, Christian Richardt, Ramesh Raskar, Rakesh Ranjan
3D reconstruction from a single-view is challenging because of the ambiguity from monocular cues and lack of information about occluded regions. Neural radiance fields (NeRF), while popular for view synthesis and 3D reconstruction, are typically reliant on multi-view images. Existing methods for single-view 3D reconstruction with NeRF rely on either data priors to hallucinate views of occluded regions, which may not be physically accurate, or shadows observed by RGB cameras, which are difficult to detect in ambient light and low albedo backgrounds. We propose using time-of-flight data captured by a single-photon avalanche diode to overcome these limitations. Our method models two-bounce optical paths with NeRF, using lidar transient data for supervision. By leveraging the advantages of both NeRF and two-bounce light measured by lidar, we demonstrate that we can reconstruct visible and occluded geometry without data priors or reliance on controlled ambient lighting or scene albedo. In addition, we demonstrate improved generalization under practical constraints on sensor spatial- and temporal-resolution. We believe our method is a promising direction as single-photon lidars become ubiquitous on consumer devices, such as phones, tablets, and headsets.
Authors: Sepideh Koohfar, Laura Dietz
Time series forecasting is a challenging task due to the existence of complex and dynamic temporal dependencies. This can lead to incorrect predictions by even the best forecasting models. Using more training data is one way to improve the accuracy, but this source is often limited. In contrast, we are building on successful denoising approaches for image generation by advocating for an end-to-end forecasting and denoising paradigm.
We propose an end-to-end forecast-blur-denoise forecasting framework by encouraging a division of labors between the forecasting and the denoising models. The initial forecasting model is directed to focus on accurately predicting the coarse-grained behavior, while the denoiser model focuses on capturing the fine-grained behavior that is locally blurred by integrating a Gaussian Process model. All three parts are interacting for the best end-to-end performance. Our extensive experiments demonstrate that our proposed approach is able to improve the forecasting accuracy of several state-of-the-art forecasting models as well as several other denoising approaches.
Authors: Enoch Solomon, Abraham Woubie, Eyael Solomon Emiru
The primary objective of this work is to present an alternative approach aimed at reducing the dependency on labeled data. Our proposed method involves utilizing autoencoder pre-training within a face image recognition task with two step processes. Initially, an autoencoder is trained in an unsupervised manner using a substantial amount of unlabeled training dataset. Subsequently, a deep learning model is trained with initialized parameters from the pre-trained autoencoder. This deep learning training process is conducted in a supervised manner, employing relatively limited labeled training dataset. During evaluation phase, face image embeddings is generated as the output of deep neural network layer. Our training is executed on the CelebA dataset, while evaluation is performed using benchmark face recognition datasets such as Labeled Faces in the Wild (LFW) and YouTube Faces (YTF). Experimental results demonstrate that by initializing the deep neural network with pre-trained autoencoder parameters achieve comparable results to state-of-the-art methods.
Authors: Yuke Li, Lixiong Chen, Guangyi Chen, Ching-Yao Chan, Kun Zhang, Stefano Anzellotti, Donglai Wei
In order to predict a pedestrian's trajectory in a crowd accurately, one has to take into account her/his underlying socio-temporal interactions with other pedestrians consistently. Unlike existing work that represents the relevant information separately, partially, or implicitly, we propose a complete representation for it to be fully and explicitly captured and analyzed. In particular, we introduce a Directed Acyclic Graph-based structure, which we term Socio-Temporal Graph (STG), to explicitly capture pair-wise socio-temporal interactions among a group of people across both space and time. Our model is built on a time-varying generative process, whose latent variables determine the structure of the STGs. We design an attention-based model named STGformer that affords an end-to-end pipeline to learn the structure of the STGs for trajectory prediction. Our solution achieves overall state-of-the-art prediction accuracy in two large-scale benchmark datasets. Our analysis shows that a person's past trajectory is critical for predicting another person's future path. Our model learns this relationship with a strong notion of socio-temporal localities. Statistics show that utilizing this information explicitly for prediction yields a noticeable performance gain with respect to the trajectory-only approaches.
Authors: Yicheng Leng, Chaowei Fang, Gen Li, Yixiang Fang, Guanbin Li
Visible watermarks, while instrumental in protecting image copyrights, frequently distort the underlying content, complicating tasks like scene interpretation and image editing. Visible watermark removal aims to eliminate the interference of watermarks and restore the background content. However, existing methods often implement watermark component removal and background restoration tasks within a singular branch, leading to residual watermarks in the predictions and ignoring cases where watermarks heavily obscure the background. To address these limitations, this study introduces the Removing Interference and Recovering Content Imaginatively (RIRCI) framework. RIRCI embodies a two-stage approach: the initial phase centers on discerning and segregating the watermark component, while the subsequent phase focuses on background content restoration. To achieve meticulous background restoration, our proposed model employs a dual-path network capable of fully exploring the intrinsic background information beneath semi-transparent watermarks and peripheral contextual information from unaffected regions. Moreover, a Global and Local Context Interaction module is built upon multi-layer perceptrons and bidirectional feature transformation for comprehensive representation modeling in the background restoration phase. The efficacy of our approach is empirically validated across two large-scale datasets, and our findings reveal a marked enhancement over existing watermark removal techniques.
Authors: Chaowei Fang, Ziyin Zhou, Junye Chen, Hanjing Su, Qingyao Wu, Guanbin Li
Point-based interactive image segmentation can ease the burden of mask annotation in applications such as semantic segmentation and image editing. However, fully extracting the target mask with limited user inputs remains challenging. We introduce a novel method, Variance-Insensitive and Target-Preserving Mask Refinement to enhance segmentation quality with fewer user inputs. Regarding the last segmentation result as the initial mask, an iterative refinement process is commonly employed to continually enhance the initial mask. Nevertheless, conventional techniques suffer from sensitivity to the variance in the initial mask. To circumvent this problem, our proposed method incorporates a mask matching algorithm for ensuring consistent inferences from different types of initial masks. We also introduce a target-aware zooming algorithm to preserve object information during downsampling, balancing efficiency and accuracy. Experiments on GrabCut, Berkeley, SBD, and DAVIS datasets demonstrate our method's state-of-the-art performance in interactive image segmentation.
Authors: Wanchao Su, Can Wang, Chen Liu, Hangzhou Han, Hongbo Fu, Jing Liao
Creating fine-retouched portrait images is tedious and time-consuming even for professional artists. There exist automatic retouching methods, but they either suffer from over-smoothing artifacts or lack generalization ability. To address such issues, we present StyleRetoucher, a novel automatic portrait image retouching framework, leveraging StyleGAN's generation and generalization ability to improve an input portrait image's skin condition while preserving its facial details. Harnessing the priors of pretrained StyleGAN, our method shows superior robustness: a). performing stably with fewer training samples and b). generalizing well on the out-domain data. Moreover, by blending the spatial features of the input image and intermediate features of the StyleGAN layers, our method preserves the input characteristics to the largest extent. We further propose a novel blemish-aware feature selection mechanism to effectively identify and remove the skin blemishes, improving the image skin condition. Qualitative and quantitative evaluations validate the great generalization capability of our method. Further experiments show StyleRetoucher's superior performance to the alternative solutions in the image retouching task. We also conduct a user perceptive study to confirm the superior retouching performance of our method over the existing state-of-the-art alternatives.
Authors: Enoch Solomon, Abraham Woubie, Eyael Solomon Emiru
Although deep learning are commonly employed for image recognition, usually huge amount of labeled training data is required, which may not always be readily available. This leads to a noticeable performance disparity when compared to state-of-the-art unsupervised face verification techniques. In this work, we propose a method to narrow this gap by leveraging an autoencoder to convert the face image vector into a novel representation. Notably, the autoencoder is trained to reconstruct neighboring face image vectors rather than the original input image vectors. These neighbor face image vectors are chosen through an unsupervised process based on the highest cosine scores with the training face image vectors. The proposed method achieves a relative improvement of 56\% in terms of EER over the baseline system on Labeled Faces in the Wild (LFW) dataset. This has successfully narrowed down the performance gap between cosine and PLDA scoring systems.
Authors: Cristian Rodriguez-Opazo, Edison Marrese-Taylor, Ehsan Abbasnejad, Hamed Damirchi, Ignacio M. Jara, Felipe Bravo-Marquez, Anton van den Hengel
Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning. Various neural architectures, spanning Transformer-based models like Vision Transformers (ViTs) to Convolutional Networks (ConvNets) like ResNets, are trained with CLIP and serve as universal backbones across diverse vision tasks. Despite utilizing the same data and training objectives, the effectiveness of representations learned by these architectures raises a critical question. Our investigation explores the differences in CLIP performance among these backbone architectures, revealing significant disparities in their classifications. Notably, normalizing these representations results in substantial performance variations. Our findings showcase a remarkable possible synergy between backbone predictions that could reach an improvement of over 20% through informed selection of the appropriate backbone. Moreover, we propose a simple, yet effective approach to combine predictions from multiple backbones, leading to a notable performance boost of up to 6.34\%. We will release the code for reproducing the results.
Authors: Shinan Zou, Chao Fan, Jianbo Xiong, Chuanfu Shen, Shiqi Yu, Jin Tang
Gait datasets are essential for gait research. However, this paper observes that present benchmarks, whether conventional constrained or emerging real-world datasets, fall short regarding covariate diversity. To bridge this gap, we undertake an arduous 20-month effort to collect a cross-covariate gait recognition (CCGR) dataset. The CCGR dataset has 970 subjects and about 1.6 million sequences; almost every subject has 33 views and 53 different covariates. Compared to existing datasets, CCGR has both population and individual-level diversity. In addition, the views and covariates are well labeled, enabling the analysis of the effects of different factors. CCGR provides multiple types of gait data, including RGB, parsing, silhouette, and pose, offering researchers a comprehensive resource for exploration. In order to delve deeper into addressing cross-covariate gait recognition, we propose parsing-based gait recognition (ParsingGait) by utilizing the newly proposed parsing data. We have conducted extensive experiments. Our main results show: 1) Cross-covariate emerges as a pivotal challenge for practical applications of gait recognition. 2) ParsingGait demonstrates remarkable potential for further advancement. 3) Alarmingly, existing SOTA methods achieve less than 43% accuracy on the CCGR, highlighting the urgency of exploring cross-covariate gait recognition. Link: https://github.com/ShinanZou/CCGR.
Authors: Xuannan Liu, Yaoyao Zhong, Xing Cui, Yuhang Zhang, Peipei Li, Weihong Deng
With extensive face images being shared on social media, there has been a notable escalation in privacy concerns. In this paper, we propose AdvCloak, an innovative framework for privacy protection using generative models. AdvCloak is designed to automatically customize class-wise adversarial masks that can maintain superior image-level naturalness while providing enhanced feature-level generalization ability. Specifically, AdvCloak sequentially optimizes the generative adversarial networks by employing a two-stage training strategy. This strategy initially focuses on adapting the masks to the unique individual faces via image-specific training and then enhances their feature-level generalization ability to diverse facial variations of individuals via person-specific training. To fully utilize the limited training data, we combine AdvCloak with several general geometric modeling methods, to better describe the feature subspace of source identities. Extensive quantitative and qualitative evaluations on both common and celebrity datasets demonstrate that AdvCloak outperforms existing state-of-the-art methods in terms of efficiency and effectiveness.
Authors: Shinan Zou, Jianbo Xiong, Chao Fan, Shiqi Yu, Jin Tang
Gait recognition is a biometric technology that has received extensive attention. Most existing gait recognition algorithms are unimodal, and a few multimodal gait recognition algorithms perform multimodal fusion only once. None of these algorithms may fully exploit the complementary advantages of the multiple modalities. In this paper, by considering the temporal and spatial characteristics of gait data, we propose a multi-stage feature fusion strategy (MSFFS), which performs multimodal fusions at different stages in the feature extraction process. Also, we propose an adaptive feature fusion module (AFFM) that considers the semantic association between silhouettes and skeletons. The fusion process fuses different silhouette areas with their more related skeleton joints. Since visual appearance changes and time passage co-occur in a gait period, we propose a multiscale spatial-temporal feature extractor (MSSTFE) to learn the spatial-temporal linkage features thoroughly. Specifically, MSSTFE extracts and aggregates spatial-temporal linkages information at different spatial scales. Combining the strategy and modules mentioned above, we propose a multi-stage adaptive feature fusion (MSAFF) neural network, which shows state-of-the-art performance in many experiments on three datasets. Besides, MSAFF is equipped with feature dimensional pooling (FD Pooling), which can significantly reduce the dimension of the gait representations without hindering the accuracy. https://github.com/ShinanZou/MSAFF
Authors: Mostafa ElAraby, Sabyasachi Sahoo, Yann Pequignot, Paul Novello, Liam Paull
Deep neural networks (DNNs) often fail silently with over-confident predictions on out-of-distribution (OOD) samples, posing risks in real-world deployments. Existing techniques predominantly emphasize either the feature representation space or the gradient norms computed with respect to DNN parameters, yet they overlook the intricate gradient distribution and the topology of classification regions. To address this gap, we introduce GRadient-aware Out-Of-Distribution detection in interpolated manifolds (GROOD), a novel framework that relies on the discriminative power of gradient space to distinguish between in-distribution (ID) and OOD samples. To build this space, GROOD relies on class prototypes together with a prototype that specifically captures OOD characteristics. Uniquely, our approach incorporates a targeted mix-up operation at an early intermediate layer of the DNN to refine the separation of gradient spaces between ID and OOD samples. We quantify OOD detection efficacy using the distance to the nearest neighbor gradients derived from the training set, yielding a robust OOD score. Experimental evaluations substantiate that the introduction of targeted input mix-upamplifies the separation between ID and OOD in the gradient space, yielding impressive results across diverse datasets. Notably, when benchmarked against ImageNet-1k, GROOD surpasses the established robustness of state-of-the-art baselines. Through this work, we establish the utility of leveraging gradient spaces and class prototypes for enhanced OOD detection for DNN in image classification.
Authors: Jay Shenoy, Axel Levy, Frédéric Poitevin, Gordon Wetzstein
X-ray free-electron lasers (XFELs) offer unique capabilities for measuring the structure and dynamics of biomolecules, helping us understand the basic building blocks of life. Notably, high-repetition-rate XFELs enable single particle imaging (X-ray SPI) where individual, weakly scattering biomolecules are imaged under near-physiological conditions with the opportunity to access fleeting states that cannot be captured in cryogenic or crystallized conditions. Existing X-ray SPI reconstruction algorithms, which estimate the unknown orientation of a particle in each captured image as well as its shared 3D structure, are inadequate in handling the massive datasets generated by these emerging XFELs. Here, we introduce X-RAI, an online reconstruction framework that estimates the structure of a 3D macromolecule from large X-ray SPI datasets. X-RAI consists of a convolutional encoder, which amortizes pose estimation over large datasets, as well as a physics-based decoder, which employs an implicit neural representation to enable high-quality 3D reconstruction in an end-to-end, self-supervised manner. We demonstrate that X-RAI achieves state-of-the-art performance for small-scale datasets in simulation and challenging experimental settings and demonstrate its unprecedented ability to process large datasets containing millions of diffraction images in an online fashion. These abilities signify a paradigm shift in X-ray SPI towards real-time capture and reconstruction.
Authors: Lei Liu, Mengya Zhang, Cheng Li, Chenglong Li, Jin Tang
Visual tracking often faces challenges such as invalid targets and decreased performance in low-light conditions when relying solely on RGB image sequences. While incorporating additional modalities like depth and infrared data has proven effective, existing multi-modal imaging platforms are complex and lack real-world applicability. In contrast, near-infrared (NIR) imaging, commonly used in surveillance cameras, can switch between RGB and NIR based on light intensity. However, tracking objects across these heterogeneous modalities poses significant challenges, particularly due to the absence of modality switch signals during tracking. To address these challenges, we propose an adaptive cross-modal object tracking algorithm called Modality-Aware Fusion Network (MAFNet). MAFNet efficiently integrates information from both RGB and NIR modalities using an adaptive weighting mechanism, effectively bridging the appearance gap and enabling a modality-aware target representation. It consists of two key components: an adaptive weighting module and a modality-specific representation module......
Authors: Pengxiang Ding, Han Zhao, Zhitao Wang, Zhenyu Wei, Shangke Lyu, Donglin Wang
The important manifestation of robot intelligence is the ability to naturally interact and autonomously make decisions. Traditional approaches to robot control often compartmentalize perception, planning, and decision-making, simplifying system design but limiting the synergy between different information streams. This compartmentalization poses challenges in achieving seamless autonomous reasoning, decision-making, and action execution. To address these limitations, a novel paradigm, named Vision-Language-Action tasks for QUAdruped Robots (QUAR-VLA), has been introduced in this paper. This approach tightly integrates visual information and instructions to generate executable actions, effectively merging perception, planning, and decision-making. The central idea is to elevate the overall intelligence of the robot. Within this framework, a notable challenge lies in aligning fine-grained instructions with visual perception information. This emphasizes the complexity involved in ensuring that the robot accurately interprets and acts upon detailed instructions in harmony with its visual observations. Consequently, we propose QUAdruped Robotic Transformer (QUART), a family of VLA models to integrate visual information and instructions from diverse modalities as input and generates executable actions for real-world robots and present QUAdruped Robot Dataset (QUARD), a large-scale multi-task dataset including navigation, complex terrain locomotion, and whole-body manipulation tasks for training QUART models. Our extensive evaluation (4000 evaluation trials) shows that our approach leads to performant robotic policies and enables QUART to obtain a range of emergent capabilities.
Authors: Dongmei Zhang, Chang Li, Ray Zhang, Shenghao Xie, Wei Xue, Xiaodong Xie, Shanghang Zhang
The superior performances of pre-trained foundation models in various visual tasks underscore their potential to enhance the 2D models' open-vocabulary ability. Existing methods explore analogous applications in the 3D space. However, most of them only center around knowledge extraction from singular foundation models, which limits the open-vocabulary ability of 3D models. We hypothesize that leveraging complementary pre-trained knowledge from various foundation models can improve knowledge transfer from 2D pre-trained visual language models to the 3D space. In this work, we propose FM-OV3D, a method of Foundation Model-based Cross-modal Knowledge Blending for Open-Vocabulary 3D Detection, which improves the open-vocabulary localization and recognition abilities of 3D model by blending knowledge from multiple pre-trained foundation models, achieving true open-vocabulary without facing constraints from original 3D datasets. Specifically, to learn the open-vocabulary 3D localization ability, we adopt the open-vocabulary localization knowledge of the Grounded-Segment-Anything model. For open-vocabulary 3D recognition ability, We leverage the knowledge of generative foundation models, including GPT-3 and Stable Diffusion models, and cross-modal discriminative models like CLIP. The experimental results on two popular benchmarks for open-vocabulary 3D object detection show that our model efficiently learns knowledge from multiple foundation models to enhance the open-vocabulary ability of the 3D model and successfully achieves state-of-the-art performance in open-vocabulary 3D object detection tasks. Code is released at https://github.com/dmzhang0425/FM-OV3D.git.
Authors: Lei Liu, Chenglong Li, Futian Wang, Longfeng Shen, Jin Tang
Cross-modal object tracking is an important research topic in the field of information fusion, and it aims to address imaging limitations in challenging scenarios by integrating switchable visible and near-infrared modalities. However, existing tracking methods face some difficulties in adapting to significant target appearance variations in the presence of modality switch. For instance, model update based tracking methods struggle to maintain stable tracking results during modality switching, leading to error accumulation and model drift. Template based tracking methods solely rely on the template information from first frame and/or last frame, which lacks sufficient representation ability and poses challenges in handling significant target appearance changes. To address this problem, we propose a prototype-based cross-modal object tracker called ProtoTrack, which introduces a novel prototype learning scheme to adapt to significant target appearance variations, for cross-modal object tracking. In particular, we design a multi-modal prototype to represent target information by multi-kind samples, including a fixed sample from the first frame and two representative samples from different modalities. Moreover, we develop a prototype generation algorithm based on two new modules to ensure the prototype representative in different challenges......
Authors: Zhenjia Li, Jinrang Jia, Yifeng Shi
In the field of autonomous driving, monocular 3D detection is a critical task which estimates 3D properties (depth, dimension, and orientation) of objects in a single RGB image. Previous works have used features in a heuristic way to learn 3D properties, without considering that inappropriate features could have adverse effects. In this paper, sample selection is introduced that only suitable samples should be trained to regress the 3D properties. To select samples adaptively, we propose a Learnable Sample Selection (LSS) module, which is based on Gumbel-Softmax and a relative-distance sample divider. The LSS module works under a warm-up strategy leading to an improvement in training stability. Additionally, since the LSS module dedicated to 3D property sample selection relies on object-level features, we further develop a data augmentation method named MixUp3D to enrich 3D property samples which conforms to imaging principles without introducing ambiguity. As two orthogonal methods, the LSS module and MixUp3D can be utilized independently or in conjunction. Sufficient experiments have shown that their combined use can lead to synergistic effects, yielding improvements that transcend the mere sum of their individual applications. Leveraging the LSS module and the MixUp3D, without any extra data, our method named MonoLSS ranks 1st in all three categories (Car, Cyclist, and Pedestrian) on KITTI 3D object detection benchmark, and achieves competitive results on both the Waymo dataset and KITTI-nuScenes cross-dataset evaluation. The code is included in the supplementary material and will be released to facilitate related academic and industrial studies.
Authors: Wenxi Yue, Jing Zhang, Kun Hu, Qiuxia Wu, Zongyuan Ge, Yong Xia, Jiebo Luo, Zhiyong Wang
Foundation models like the Segment Anything Model (SAM) have demonstrated promise in generic object segmentation. However, directly applying SAM to surgical instrument segmentation presents key challenges. First, SAM relies on per-frame point-or-box prompts which complicate surgeon-computer interaction. Also, SAM yields suboptimal performance on segmenting surgical instruments, owing to insufficient surgical data in its pre-training as well as the complex structure and fine-grained details of various surgical instruments. To address these challenges, in this paper, we investigate text promptable surgical instrument segmentation and propose SP-SAM (SurgicalPart-SAM), a novel efficient-tuning approach that integrates surgical instrument structure knowledge with the generic segmentation knowledge of SAM. Specifically, we achieve this by proposing (1) collaborative prompts in the text form "[part name] of [instrument category name]" that decompose instruments into fine-grained parts; (2) a Cross-Modal Prompt Encoder that encodes text prompts jointly with visual embeddings into discriminative part-level representations; and (3) a Part-to-Whole Selective Fusion and a Hierarchical Decoding strategy that selectively assemble the part-level representations into a whole for accurate instrument segmentation. Built upon them, SP-SAM acquires a better capability to comprehend surgical instrument structures and distinguish between various categories. Extensive experiments on both the EndoVis2018 and EndoVis2017 datasets demonstrate SP-SAM's state-of-the-art performance with minimal tunable parameters. Code is at https://github.com/wenxi-yue/SurgicalPart-SAM.
Authors: Seungjun An, Seonghoon Park, Gyeongnyeon Kim, Jeongyeol Baek, Byeongwon Lee, Seungryong Kim
With the increasing importance of video data in real-world applications, there is a rising need for efficient object detection methods that utilize temporal information. While existing video object detection (VOD) techniques employ various strategies to address this challenge, they typically depend on locally adjacent frames or randomly sampled images within a clip. Although recent Transformer-based VOD methods have shown promising results, their reliance on multiple inputs and additional network complexity to incorporate temporal information limits their practical applicability. In this paper, we propose a novel approach to single image object detection, called Context Enhanced TRansformer (CETR), by incorporating temporal context into DETR using a newly designed memory module. To efficiently store temporal information, we construct a class-wise memory that collects contextual information across data. Additionally, we present a classification-based sampling technique to selectively utilize the relevant memory for the current image. In the testing, We introduce a test-time memory adaptation method that updates individual memory functions by considering the test distribution. Experiments with CityCam and ImageNet VID datasets exhibit the efficiency of the framework on various video systems. The project page and code will be made available at: https://ku-cvlab.github.io/CETR.
Authors: Anish Madan, Neehar Peri, Shu Kong, Deva Ramanan
Few-shot object detection (FSOD) benchmarks have advanced techniques for detecting new categories with limited annotations. Existing benchmarks repurpose well-established datasets like COCO by partitioning categories into base and novel classes for pre-training and fine-tuning respectively. However, these benchmarks do not reflect how FSOD is deployed in practice. Rather than only pre-training on a small number of base categories, we argue that it is more practical to fine-tune a foundation model (e.g., a vision-language model (VLM) pre-trained on web-scale data) for a target domain. Surprisingly, we find that zero-shot inference from VLMs like GroundingDINO significantly outperforms the state-of-the-art (48.3 vs. 33.1 AP) on COCO. However, such zero-shot models can still be misaligned to target concepts of interest. For example, trailers on the web may be different from trailers in the context of autonomous vehicles. In this work, we propose Foundational FSOD, a new benchmark protocol that evaluates detectors pre-trained on any external datasets and fine-tuned on K-shots per target class. Further, we note that current FSOD benchmarks are actually federated datasets containing exhaustive annotations for each category on a subset of the data. We leverage this insight to propose simple strategies for fine-tuning VLMs with federated losses. We demonstrate the effectiveness of our approach on LVIS and nuImages, improving over prior work by 5.9 AP.
Authors: Fu-Jen Tsai, Yan-Tsung Peng, Chen-Yu Chang, Chan-Yu Li, Yen-Yu Lin, Chung-Chi Tsai, Chia-Wen Lin
Video restoration is a low-level vision task that seeks to restore clean, sharp videos from quality-degraded frames. One would use the temporal information from adjacent frames to make video restoration successful. Recently, the success of the Transformer has raised awareness in the computer-vision community. However, its self-attention mechanism requires much memory, which is unsuitable for high-resolution vision tasks like video restoration. In this paper, we propose ViStripformer (Video Stripformer), which utilizes spatio-temporal strip attention to catch long-range data correlations, consisting of intra-frame strip attention (Intra-SA) and inter-frame strip attention (Inter-SA) for extracting spatial and temporal information. It decomposes video frames into strip-shaped features in horizontal and vertical directions for Intra-SA and Inter-SA to address degradation patterns with various orientations and magnitudes. Besides, ViStripformer is an effective and efficient transformer architecture with much lower memory usage than the vanilla transformer. Extensive experiments show that the proposed model achieves superior results with fast inference time on video restoration tasks, including video deblurring, demoireing, and deraining.
Authors: Minghui Liao, Guojia Wan, Bo Du
Determining the types of neurons within a nervous system plays a significant role in the analysis of brain connectomics and the investigation of neurological diseases. However, the efficiency of utilizing anatomical, physiological, or molecular characteristics of neurons is relatively low and costly. With the advancements in electron microscopy imaging and analysis techniques for brain tissue, we are able to obtain whole-brain connectome consisting neuronal high-resolution morphology and connectivity information. However, few models are built based on such data for automated neuron classification. In this paper, we propose NeuNet, a framework that combines morphological information of neurons obtained from skeleton and topological information between neurons obtained from neural circuit. Specifically, NeuNet consists of three components, namely Skeleton Encoder, Connectome Encoder, and Readout Layer. Skeleton Encoder integrates the local information of neurons in a bottom-up manner, with a one-dimensional convolution in neural skeleton's point data; Connectome Encoder uses a graph neural network to capture the topological information of neural circuit; finally, Readout Layer fuses the above two information and outputs classification results. We reprocess and release two new datasets for neuron classification task from volume electron microscopy(VEM) images of human brain cortex and Drosophila brain. Experiments on these two datasets demonstrated the effectiveness of our model with accuracy of 0.9169 and 0.9363, respectively. Code and data are available at: https://github.com/WHUminghui/NeuNet.
Authors: Hongliu Cao, Minh Nhat Do, Alexis Ravanel, Eoin Thomas
Face recognition has been used more and more in real world applications in recent years. However, when the skin color bias is coupled with intra-personal variations like harsh illumination, the face recognition task is more likely to fail, even during human inspection. Face normalization methods try to deal with such challenges by removing intra-personal variations from an input image while keeping the identity the same. However, most face normalization methods can only remove one or two variations and ignore dataset biases such as skin color bias. The outputs of many face normalization methods are also not realistic to human observers. In this work, a style based face normalization model (StyleFNM) is proposed to remove most intra-personal variations including large changes in pose, bad or harsh illumination, low resolution, blur, facial expressions, and accessories like sunglasses among others. The dataset bias is also dealt with in this paper by controlling a pretrained GAN to generate a balanced dataset of passport-like images. The experimental results show that StyleFNM can generate more realistic outputs and can improve significantly the accuracy and fairness of face recognition systems.
Authors: Rohith Peddi, Shivvrat Arya, Bharath Challa, Likhitha Pallapothula, Akshay Vyas, Jikai Wang, Qifan Zhang, Vasundhara Komaragiri, Eric Ragan, Nicholas Ruozzi, Yu Xiang, Vibhav Gogate
Following step-by-step procedures is an essential component of various activities carried out by individuals in their daily lives. These procedures serve as a guiding framework that helps to achieve goals efficiently, whether it is assembling furniture or preparing a recipe. However, the complexity and duration of procedural activities inherently increase the likelihood of making errors. Understanding such procedural activities from a sequence of frames is a challenging task that demands an accurate interpretation of visual information and the ability to reason about the structure of the activity. To this end, we collect a new egocentric 4D dataset, CaptainCook4D, comprising 384 recordings (94.5 hours) of people performing recipes in real kitchen environments. This dataset consists of two distinct types of activity: one in which participants adhere to the provided recipe instructions and another in which they deviate and induce errors. We provide 5.3K step annotations and 10K fine-grained action annotations and benchmark the dataset for the following tasks: supervised error recognition, multistep localization, and procedure learning
Authors: Wenshuai Xu, Zhenbo Xu
The key technology to overcome the drawbacks of hyperspectral imaging (expensive, high capture delay, and low spatial resolution) and make it widely applicable is to select only a few representative bands from hundreds of bands. However, current band selection (BS) methods face challenges in fair comparisons due to inconsistent train/validation settings, including the number of bands, dataset splits, and retraining settings. To make BS methods easy and reproducible, this paper presents the first band selection search benchmark (BSS-Bench) containing 52k training and evaluation records of numerous band combinations (BC) with different backbones for various hyperspectral analysis tasks. The creation of BSS-Bench required a significant computational effort of 1.26k GPU days. By querying BSS-Bench, BS experiments can be performed easily and reproducibly, and the gap between the searched result and the best achievable performance can be measured. Based on BSS-Bench, we further discuss the impact of various factors on BS, such as the number of bands, unsupervised statistics, and different backbones. In addition to BSS-Bench, we present an effective one-shot BS method called Single Combination One Shot (SCOS), which learns the priority of any BCs through one-time training, eliminating the need for repetitive retraining on different BCs. Furthermore, the search process of SCOS is flexible and does not require training, making it efficient and effective. Our extensive evaluations demonstrate that SCOS outperforms current BS methods on multiple tasks, even with much fewer bands. Our BSS-Bench and codes are available in the supplementary material and will be publicly available.
Authors: Liang Peng, Songyue Cai, Zongqian Wu, Huifang Shang, Xiaofeng Zhu, Xiaoxiao Li
Prompt learning has demonstrated impressive efficacy in the fine-tuning of multimodal large models to a wide range of downstream tasks. Nonetheless, applying existing prompt learning methods for the diagnosis of neurological disorder still suffers from two issues: (i) existing methods typically treat all patches equally, despite the fact that only a small number of patches in neuroimaging are relevant to the disease, and (ii) they ignore the structural information inherent in the brain connection network which is crucial for understanding and diagnosing neurological disorders. To tackle these issues, we introduce a novel prompt learning model by learning graph prompts during the fine-tuning process of multimodal large models for diagnosing neurological disorders. Specifically, we first leverage GPT-4 to obtain relevant disease concepts and compute semantic similarity between these concepts and all patches. Secondly, we reduce the weight of irrelevant patches according to the semantic similarity between each patch and disease-related concepts. Moreover, we construct a graph among tokens based on these concepts and employ a graph convolutional network layer to extract the structural information of the graph, which is used to prompt the pre-trained multimodal large models for diagnosing neurological disorders. Extensive experiments demonstrate that our method achieves superior performance for neurological disorder diagnosis compared with state-of-the-art methods and validated by clinicians.
Authors: Neha Sengar, Indra Kumari, Jihui Lee, Dongsoo Har
Driver distraction is a principal cause of traffic accidents. In a study conducted by the National Highway Traffic Safety Administration, engaging in activities such as interacting with in-car menus, consuming food or beverages, or engaging in telephonic conversations while operating a vehicle can be significant sources of driver distraction. From this viewpoint, this paper introduces a novel method for detection of driver distraction using multi-view driver action images. The proposed method is a vision transformer-based framework with pose estimation and action inference, namely PoseViNet. The motivation for adding posture information is to enable the transformer to focus more on key features. As a result, the framework is more adept at identifying critical actions. The proposed framework is compared with various state-of-the-art models using SFD3 dataset representing 10 behaviors of drivers. It is found from the comparison that the PoseViNet outperforms these models. The proposed framework is also evaluated with the SynDD1 dataset representing 16 behaviors of driver. As a result, the PoseViNet achieves 97.55% validation accuracy and 90.92% testing accuracy with the challenging dataset.
Authors: Mirela Ostrek, Soubhik Sanyal, Carol O'Sullivan, Michael J. Black, Justus Thies
Despite significant progress in generative image synthesis and full-body generation in particular, state-of-the-art methods are either context-independent, overly reliant to text prompts, or bound to the curated training datasets, such as fashion images with monotonous backgrounds. Here, our goal is to generate people in clothing that is semantically appropriate for a given scene. To this end, we present ESP, a novel method for context-aware full-body generation, that enables photo-realistic inpainting of people into existing "in-the-wild" photographs. ESP is conditioned on a 2D pose and contextual cues that are extracted from the environment photograph and integrated into the generation process. Our models are trained on a dataset containing a set of in-the-wild photographs of people covering a wide range of different environments. The method is analyzed quantitatively and qualitatively, and we show that ESP outperforms state-of-the-art on the task of contextual full-body generation.
Authors: Till Beemelmanns, Wassim Zahr, Lutz Eckstein
Vision Transformers (ViTs) have achieved state-of-the-art results on various computer vision tasks, including 3D object detection. However, their end-to-end implementation also makes ViTs less explainable, which can be a challenge for deploying them in safety-critical applications, such as autonomous driving, where it is important for authorities, developers, and users to understand the model's reasoning behind its predictions. In this paper, we propose a novel method for generating saliency maps for a DetR-like ViT with multiple camera inputs used for 3D object detection. Our method is based on the raw attention and is more efficient than gradient-based methods. We evaluate the proposed method on the nuScenes dataset using extensive perturbation tests and show that it outperforms other explainability methods in terms of visual quality and quantitative metrics. We also demonstrate the importance of aggregating attention across different layers of the transformer. Our work contributes to the development of explainable AI for ViTs, which can help increase trust in AI applications by establishing more transparency regarding the inner workings of AI models.
Authors: Xiaoyue Duan, Shuhao Cui, Guoliang Kang, Baochang Zhang, Zhengcong Fei, Mingyuan Fan, Junshi Huang
Consistent editing of real images is a challenging task, as it requires performing non-rigid edits (e.g., changing postures) to the main objects in the input image without changing their identity or attributes. To guarantee consistent attributes, some existing methods fine-tune the entire model or the textual embedding for structural consistency, but they are time-consuming and fail to perform non-rigid edits. Other works are tuning-free, but their performances are weakened by the quality of Denoising Diffusion Implicit Model (DDIM) reconstruction, which often fails in real-world scenarios. In this paper, we present a novel approach called Tuning-free Inversion-enhanced Control (TIC), which directly correlates features from the inversion process with those from the sampling process to mitigate the inconsistency in DDIM reconstruction. Specifically, our method effectively obtains inversion features from the key and value features in the self-attention layers, and enhances the sampling process by these inversion features, thus achieving accurate reconstruction and content-consistent editing. To extend the applicability of our method to general editing scenarios, we also propose a mask-guided attention concatenation strategy that combines contents from both the inversion and the naive DDIM editing processes. Experiments show that the proposed method outperforms previous works in reconstruction and consistent editing, and produces impressive results in various settings.
Authors: Yifu Liu, Xiaoxia Li, Zhiling Luo, Wei Zhou
Existing data-driven methods for garment animation, usually driven by linear skinning, although effective on tight garments, do not handle loose-fitting garments with complex deformations well. To address these limitations, we develop a garment generative model based on deformation decomposition to efficiently simulate loose garment deformation without directly using linear skinning. Specifically, we learn a garment generative space with the proposed generative model, where we decouple the latent representation into unposed deformed garments and dynamic offsets during the decoding stage. With explicit garment deformations decomposition, our generative model is able to generate complex pose-driven deformations on canonical garment shapes. Furthermore, we learn to transfer the body motions and previous state of the garment to the latent space to regenerate dynamic results. In addition, we introduce a detail enhancement module in an adversarial training setup to learn high-frequency wrinkles. We demonstrate our method outperforms state-of-the-art data-driven alternatives through extensive experiments and show qualitative and quantitative analysis of results.
Authors: Iris Dominguez-Catena, Daniel Paternain, Mikel Galar
In the last few years, Artificial Intelligence systems have become increasingly widespread. Unfortunately, these systems can share many biases with human decision-making, including demographic biases. Often, these biases can be traced back to the data used for training, where large uncurated datasets have become the norm. Despite our knowledge of these biases, we still lack general tools to detect and quantify them, as well as to compare the biases in different datasets. Thus, in this work, we propose DSAP (Demographic Similarity from Auxiliary Profiles), a two-step methodology for comparing the demographic composition of two datasets. DSAP can be deployed in three key applications: to detect and characterize demographic blind spots and bias issues across datasets, to measure dataset demographic bias in single datasets, and to measure dataset demographic shift in deployment scenarios. An essential feature of DSAP is its ability to robustly analyze datasets without explicit demographic labels, offering simplicity and interpretability for a wide range of situations. To show the usefulness of the proposed methodology, we consider the Facial Expression Recognition task, where demographic bias has previously been found. The three applications are studied over a set of twenty datasets with varying properties. The code is available at https://github.com/irisdominguez/DSAP.
Authors: Ali Abdari, Alex Falcon, Giuseppe Serra
Recently, the Metaverse is becoming increasingly attractive, with millions of users accessing the many available virtual worlds. However, how do users find the one Metaverse which best fits their current interests? So far, the search process is mostly done by word of mouth, or by advertisement on technology-oriented websites. However, the lack of search engines similar to those available for other multimedia formats (e.g., YouTube for videos) is showing its limitations, since it is often cumbersome to find a Metaverse based on some specific interests using the available methods, while also making it difficult to discover user-created ones which lack strong advertisement. To address this limitation, we propose to use language to naturally describe the desired contents of the Metaverse a user wishes to find. Second, we highlight that, differently from more conventional 3D scenes, Metaverse scenarios represent a more complex data format since they often contain one or more types of multimedia which influence the relevance of the scenario itself to a user query. Therefore, in this work, we create a novel task, called Text-to-Metaverse retrieval, which aims at modeling these aspects while also taking the cross-modal relations with the textual data into account. Since we are the first ones to tackle this problem, we also collect a dataset of 33000 Metaverses, each of which consists of a 3D scene enriched with multimedia content. Finally, we design and implement a deep learning framework based on contrastive learning, resulting in a thorough experimental setup.
Authors: Yitong Deng, Hong-Xing Yu, Diyang Zhang, Jiajun Wu, Bo Zhu
We introduce Neural Flow Maps, a novel simulation method bridging the emerging paradigm of implicit neural representations with fluid simulation based on the theory of flow maps, to achieve state-of-the-art simulation of inviscid fluid phenomena. We devise a novel hybrid neural field representation, Spatially Sparse Neural Fields (SSNF), which fuses small neural networks with a pyramid of overlapping, multi-resolution, and spatially sparse grids, to compactly represent long-term spatiotemporal velocity fields at high accuracy. With this neural velocity buffer in hand, we compute long-term, bidirectional flow maps and their Jacobians in a mechanistically symmetric manner, to facilitate drastic accuracy improvement over existing solutions. These long-range, bidirectional flow maps enable high advection accuracy with low dissipation, which in turn facilitates high-fidelity incompressible flow simulations that manifest intricate vortical structures. We demonstrate the efficacy of our neural fluid simulation in a variety of challenging simulation scenarios, including leapfrogging vortices, colliding vortices, vortex reconnections, as well as vortex generation from moving obstacles and density differences. Our examples show increased performance over existing methods in terms of energy conservation, visual complexity, adherence to experimental observations, and preservation of detailed vortical structures.
Authors: Zihua Liu, Yizhou Li, Masatoshi Okutomi
Despite the remarkable progress facilitated by learning-based stereo-matching algorithms, the performance in the ill-conditioned regions, such as the occluded regions, remains a bottleneck. Due to the limited receptive field, existing CNN-based methods struggle to handle these ill-conditioned regions effectively. To address this issue, this paper introduces a novel attention-based stereo-matching network called Global Occlusion-Aware Transformer (GOAT) to exploit long-range dependency and occlusion-awareness global context for disparity estimation. In the GOAT architecture, a parallel disparity and occlusion estimation module PDO is proposed to estimate the initial disparity map and the occlusion mask using a parallel attention mechanism. To further enhance the disparity estimates in the occluded regions, an occlusion-aware global aggregation module (OGA) is proposed. This module aims to refine the disparity in the occluded regions by leveraging restricted global correlation within the focus scope of the occluded areas. Extensive experiments were conducted on several public benchmark datasets including SceneFlow, KITTI 2015, and Middlebury. The results show that the proposed GOAT demonstrates outstanding performance among all benchmarks, particularly in the occluded regions.
Authors: Miriam Jäger, Steven Landgraf, Boris Jutzi
In the fields of computer graphics, computer vision and photogrammetry, Neural Radiance Fields (NeRFs) are a major topic driving current research and development. However, the quality of NeRF-generated 3D scene reconstructions and subsequent surface reconstructions, heavily relies on the network output, particularly the density. Regarding this critical aspect, we propose to utilize NeRF-Ensembles that provide a density uncertainty estimate alongside the mean density. We demonstrate that data constraints such as low-quality images and poses lead to a degradation of the training process, increased density uncertainty and decreased predicted density. Even with high-quality input data, the density uncertainty varies based on scene constraints such as acquisition constellations, occlusions and material properties. NeRF-Ensembles not only provide a tool for quantifying the uncertainty but exhibit two promising advantages: Enhanced robustness and artifact removal. Through the utilization of NeRF-Ensembles instead of single NeRFs, small outliers are removed, yielding a smoother output with improved completeness of structures. Furthermore, applying percentile-based thresholds on density uncertainty outliers proves to be effective for the removal of large (foggy) artifacts in post-processing. We conduct our methodology on 3 different datasets: (i) synthetic benchmark dataset, (ii) real benchmark dataset, (iii) real data under realistic recording conditions and sensors.
Authors: Joaquin Rodriguez, Lew-Fock-Chong Lew-Yan-Voon, Renato Martins, Olivier Morel
Polarization information of the light can provide rich cues for computer vision and scene understanding tasks, such as the type of material, pose, and shape of the objects. With the advent of new and cheap polarimetric sensors, this imaging modality is becoming accessible to a wider public for solving problems such as pose estimation, 3D reconstruction, underwater navigation, and depth estimation. However, we observe several limitations regarding the usage of this sensorial modality, as well as a lack of standards and publicly available tools to analyze polarization images. Furthermore, although polarization camera manufacturers usually provide acquisition tools to interface with their cameras, they rarely include processing algorithms that make use of the polarization information. In this paper, we review recent advances in applications that involve polarization imaging, including a comprehensive survey of recent advances on polarization for vision and robotics perception tasks. We also introduce a complete software toolkit that provides common standards to communicate with and process information from most of the existing micro-grid polarization cameras on the market. The toolkit also implements several image processing algorithms for this modality, and it is publicly available on GitHub: https://github.com/vibot-lab/Pola4all_JEI_2023.
Authors: Yifei Chen, Binfeng Zou, Zhaoxin Guo, Yiyu Huang, Yifan Huang, Feiwei Qin, Qinhai Li, Changmiao Wang
Pulmonary embolism (PE) is a prevalent lung disease that can lead to right ventricular hypertrophy and failure in severe cases, ranking second in severity only to myocardial infarction and sudden death. Pulmonary artery CT angiography (CTPA) is a widely used diagnostic method for PE. However, PE detection presents challenges in clinical practice due to limitations in imaging technology. CTPA can produce noises similar to PE, making confirmation of its presence time-consuming and prone to overdiagnosis. Nevertheless, the traditional segmentation method of PE can not fully consider the hierarchical structure of features, local and global spatial features of PE CT images. In this paper, we propose an automatic PE segmentation method called SCUNet++ (Swin Conv UNet++). This method incorporates multiple fusion dense skip connections between the encoder and decoder, utilizing the Swin Transformer as the encoder. And fuses features of different scales in the decoder subnetwork to compensate for spatial information loss caused by the inevitable downsampling in Swin-UNet or other state-of-the-art methods, effectively solving the above problem. We provide a theoretical analysis of this method in detail and validate it on publicly available PE CT image datasets FUMPE and CAD-PE. The experimental results indicate that our proposed method achieved a Dice similarity coefficient (DSC) of 83.47% and a Hausdorff distance 95th percentile (HD95) of 3.83 on the FUMPE dataset, as well as a DSC of 83.42% and an HD95 of 5.10 on the CAD-PE dataset. These findings demonstrate that our method exhibits strong performance in PE segmentation tasks, potentially enhancing the accuracy of automatic segmentation of PE and providing a powerful diagnostic tool for clinical physicians. Our source code and new FUMPE dataset are available at https://github.com/JustlfC03/SCUNet-plusplus.
Authors: Elias Marks, Jonas Bömer, Federico Magistri, Anurag Sah, Jens Behley, Cyrill Stachniss
Agricultural production is facing severe challenges in the next decades induced by climate change and the need for sustainability, reducing its impact on the environment. Advancements in field management through non-chemical weeding by robots in combination with monitoring of crops by autonomous unmanned aerial vehicles (UAVs) and breeding of novel and more resilient crop varieties are helpful to address these challenges. The analysis of plant traits, called phenotyping, is an essential activity in plant breeding, it however involves a great amount of manual labor. With this paper, we address the problem of automatic fine-grained organ-level geometric analysis needed for precision phenotyping. As the availability of real-world data in this domain is relatively scarce, we propose a novel dataset that was acquired using UAVs capturing high-resolution images of a real breeding trial containing 48 plant varieties and therefore covering great morphological and appearance diversity. This enables the development of approaches for autonomous phenotyping that generalize well to different varieties. Based on overlapping high-resolution images from multiple viewing angles, we compute photogrammetric dense point clouds and provide detailed and accurate point-wise labels for plants, leaves, and salient points as the tip and the base. Additionally, we include measurements of phenotypic traits performed by experts from the German Federal Plant Variety Office on the real plants, allowing the evaluation of new approaches not only on segmentation and keypoint detection but also directly on the downstream tasks. The provided labeled point clouds enable fine-grained plant analysis and support further progress in the development of automatic phenotyping approaches, but also enable further research in surface reconstruction, point cloud completion, and semantic interpretation of point clouds.
Authors: Brian Sifringer, Alexandre Alahi
This paper explores the intersection of Discrete Choice Modeling (DCM) and machine learning, focusing on the integration of image data into DCM's utility functions and its impact on model interpretability. We investigate the consequences of embedding high-dimensional image data that shares isomorphic information with traditional tabular inputs within a DCM framework. Our study reveals that neural network (NN) components learn and replicate tabular variable representations from images when co-occurrences exist, thereby compromising the interpretability of DCM parameters. We propose and benchmark two methodologies to address this challenge: architectural design adjustments to segregate redundant information, and isomorphic information mitigation through source information masking and inpainting. Our experiments, conducted on a semi-synthetic dataset, demonstrate that while architectural modifications prove inconclusive, direct mitigation at the data source shows to be a more effective strategy in maintaining the integrity of DCM's interpretable parameters. The paper concludes with insights into the applicability of our findings in real-world settings and discusses the implications for future research in hybrid modeling that combines complex data modalities. Full control of tabular and image data congruence is attained by using the MIT moral machine dataset, and both inputs are merged into a choice model by deploying the Learning Multinomial Logit (L-MNL) framework.
Authors: Qiang Wan, Zilong Huang, Bingyi Kang, Jiashi Feng, Li Zhang
The issue of generative pretraining for vision models has persisted as a long-standing conundrum. At present, the text-to-image (T2I) diffusion model demonstrates remarkable proficiency in generating high-definition images matching textual inputs, a feat made possible through its pre-training on large-scale image-text pairs. This leads to a natural inquiry: can diffusion models be utilized to tackle visual perception tasks? In this paper, we propose a simple yet effective scheme to harness a diffusion model for visual perception tasks. Our key insight is to introduce learnable embeddings (meta prompts) to the pre-trained diffusion models to extract proper features for perception. The effect of meta prompts are two-fold. First, as a direct replacement of the text embeddings in the T2I models, it can activate task-relevant features during feature extraction. Second, it will be used to re-arrange the extracted features to ensures that the model focuses on the most pertinent features for the task on hand. Additionally, we design a recurrent refinement training strategy that fully leverages the property of diffusion models, thereby yielding stronger visual features. Extensive experiments across various benchmarks validate the effectiveness of our approach. Our approach achieves new performance records in depth estimation tasks on NYU depth V2 and KITTI, and in semantic segmentation task on CityScapes. Concurrently, the proposed method attains results comparable to the current state-of-the-art in semantic segmentation on ADE20K and pose estimation on COCO datasets, further exemplifying its robustness and versatility.
Authors: Rizhong Lin, Ali Gholipour, Jean-Philippe Thiran, Davood Karimi, Hamza Kebiri, Meritxell Bach Cuadra
Deep learning models have shown great promise in estimating tissue microstructure from limited diffusion magnetic resonance imaging data. However, these models face domain shift challenges when test and train data are from different scanners and protocols, or when the models are applied to data with inherent variations such as the developing brains of infants and children scanned at various ages. Several techniques have been proposed to address some of these challenges, such as data harmonization or domain adaptation in the adult brain. However, those techniques remain unexplored for the estimation of fiber orientation distribution functions in the rapidly developing brains of infants. In this work, we extensively investigate the age effect and domain shift within and across two different cohorts of 201 newborns and 165 babies using the Method of Moments and fine-tuning strategies. Our results show that reduced variations in the microstructural development of babies in comparison to newborns directly impact the deep learning models' cross-age performance. We also demonstrate that a small number of target domain samples can significantly mitigate domain shift problems.
Authors: Alireza Ganjdanesh, Shangqian Gao, Hirad Alipanah, Heng Huang
Generative Adversarial Networks (GANs) have shown remarkable success in modeling complex data distributions for image-to-image translation. Still, their high computational demands prohibit their deployment in practical scenarios like edge devices. Existing GAN compression methods mainly rely on knowledge distillation or convolutional classifiers' pruning techniques. Thus, they neglect the critical characteristic of GANs: their local density structure over their learned manifold. Accordingly, we approach GAN compression from a new perspective by explicitly encouraging the pruned model to preserve the density structure of the original parameter-heavy model on its learned manifold. We facilitate this objective for the pruned model by partitioning the learned manifold of the original generator into local neighborhoods around its generated samples. Then, we propose a novel pruning objective to regularize the pruned model to preserve the local density structure over each neighborhood, resembling the kernel density estimation method. Also, we develop a collaborative pruning scheme in which the discriminator and generator are pruned by two pruning agents. We design the agents to capture interactions between the generator and discriminator by exchanging their peer's feedback when determining corresponding models' architectures. Thanks to such a design, our pruning method can efficiently find performant sub-networks and can maintain the balance between the generator and discriminator more effectively compared to baselines during pruning, thereby showing more stable pruning dynamics. Our experiments on image translation GAN models, Pix2Pix and CycleGAN, with various benchmark datasets and architectures demonstrate our method's effectiveness.
Authors: Junli Fang, João F. C. Mota, Baoshan Lu, Weicheng Zhang, Xuemin Hong
The joint source coding and modulation (JSCM) framework was enabled by recent developments in deep learning, which allows to automatically learn from data, and in an end-to-end fashion, the best compression codes and modulation schemes. In this paper, we show the existence of a strict tradeoff between channel rate, distortion, perception, and classification accuracy in a JSCM scenario. We then propose two image compression methods to navigate that tradeoff: an inverse-domain generative adversarial network (ID-GAN), which achieves extreme compression, and a simpler, heuristic method that reveals insights about the performance of ID-GAN. Experiment results not only corroborate the theoretical findings, but also demonstrate that the proposed ID-GAN algorithm significantly improves system performance compared to traditional separation-based methods and recent deep JSCM architectures.
Authors: David de la Rosa, Antonio J Rivera, María J del Jesus, Francisco Charte
Photo-trapping cameras are widely employed for wildlife monitoring. Those cameras take photographs when motion is detected to capture images where animals appear. A significant portion of these images are empty - no wildlife appears in the image. Filtering out those images is not a trivial task since it requires hours of manual work from biologists. Therefore, there is a notable interest in automating this task. Automatic discarding of empty photo-trapping images is still an open field in the area of Machine Learning. Existing solutions often rely on state-of-the-art supervised convolutional neural networks that require the annotation of the images in the training phase. PARDINUS (Weakly suPervised discARDINg of photo-trapping empty images based on aUtoencoderS) is constructed on the foundation of weakly supervised learning and proves that this approach equals or even surpasses other fully supervised methods that require further labeling work.
Authors: Jinpeng Liu, Wenxun Dai, Chunyu Wang, Yiji Cheng, Yansong Tang, Xin Tong
Conventional text-to-motion generation methods are usually trained on limited text-motion pairs, making them hard to generalize to open-world scenarios. Some works use the CLIP model to align the motion space and the text space, aiming to enable motion generation from natural language motion descriptions. However, they are still constrained to generate limited and unrealistic in-place motions. To address these issues, we present a divide-and-conquer framework named PRO-Motion, which consists of three modules as motion planner, posture-diffuser and go-diffuser. The motion planner instructs Large Language Models (LLMs) to generate a sequence of scripts describing the key postures in the target motion. Differing from natural languages, the scripts can describe all possible postures following very simple text templates. This significantly reduces the complexity of posture-diffuser, which transforms a script to a posture, paving the way for open-world generation. Finally, go-diffuser, implemented as another diffusion model, estimates whole-body translations and rotations for all postures, resulting in realistic motions. Experimental results have shown the superiority of our method with other counterparts, and demonstrated its capability of generating diverse and realistic motions from complex open-world prompts such as "Experiencing a profound sense of joy". The project page is available at https://moonsliu.github.io/Pro-Motion.
Authors: Tanish Baranwal, Jan Lebert, Jan Christoph
Electrical waves in the heart form rotating spiral or scroll waves during life-threatening arrhythmias such as atrial or ventricular fibrillation. The wave dynamics are typically modeled using coupled partial differential equations, which describe reaction-diffusion dynamics in excitable media. More recently, data-driven generative modeling has emerged as an alternative to generate spatio-temporal patterns in physical and biological systems. Here, we explore denoising diffusion probabilistic models for the generative modeling of electrical wave patterns in cardiac tissue. We trained diffusion models with simulated electrical wave patterns to be able to generate such wave patterns in unconditional and conditional generation tasks. For instance, we explored inpainting tasks, such as reconstructing three-dimensional wave dynamics from superficial two-dimensional measurements, and evolving and generating parameter-specific dynamics. We characterized and compared the diffusion-generated solutions to solutions obtained with biophysical models and found that diffusion models learn to replicate spiral and scroll waves dynamics so well that they could serve as an alternative data-driven approach for the modeling of excitation waves in cardiac tissue. For instance, we found that it is possible to initiate ventricular fibrillation (VF) dynamics instantaneously without having to apply pacing protocols in order to induce wavebreak. The VF dynamics can be created in arbitrary ventricular geometries and can be evolved over time. However, we also found that diffusion models `hallucinate' wave patterns when given insufficient constraints. Regardless of these limitations, diffusion models are an interesting and powerful tool with many potential applications in cardiac arrhythmia research and diagnostics.
Authors: Ziqiang Wu, Bingpeng Ma
Text-based person search aims to simultaneously localize and identify the target person based on query text from uncropped scene images, which can be regarded as the unified task of person detection and text-based person retrieval task. In this work, we propose a large-scale benchmark dataset named PRW-TPS-CN based on the widely used person search dataset PRW. Our dataset contains 47,102 sentences, which means there is quite more information than existing dataset. These texts precisely describe the person images from top to bottom, which in line with the natural description order. We also provide both Chinese and English descriptions in our dataset for more comprehensive evaluation. These characteristics make our dataset more applicable. To alleviate the inconsistency between person detection and text-based person retrieval, we take advantage of the rich texts in PRW-TPS-CN dataset. We propose to aggregate multiple texts as text prototypes to maintain the prominent text features of a person, which can better reflect the whole character of a person. The overall prototypes lead to generating the image attention map to eliminate the detection misalignment causing the decrease of text-based person retrieval. Thus, the inconsistency between person detection and text-based person retrieval is largely alleviated. We conduct extensive experiments on the PRW-TPS-CN dataset. The experimental results show the PRW-TPS-CN dataset's effectiveness and the state-of-the-art performance of our approach.
Authors: Max Ku, Dongfu Jiang, Cong Wei, Xiang Yue, Wenhu Chen
In the rapidly advancing field of conditional image generation research, challenges such as limited explainability lie in effectively evaluating the performance and capabilities of various models. This paper introduces VIESCORE, a Visual Instruction-guided Explainable metric for evaluating any conditional image generation tasks. VIESCORE leverages general knowledge from Multimodal Large Language Models (MLLMs) as the backbone and does not require training or fine-tuning. We evaluate VIESCORE on seven prominent tasks in conditional image tasks and found: (1) VIESCORE (GPT4-v) achieves a high Spearman correlation of 0.3 with human evaluations, while the human-to-human correlation is 0.45. (2) VIESCORE (with open-source MLLM) is significantly weaker than GPT-4v in evaluating synthetic images. (3) VIESCORE achieves a correlation on par with human ratings in the generation tasks but struggles in editing tasks. With these results, we believe VIESCORE shows its great potential to replace human judges in evaluating image synthesis tasks.
Authors: Honghao Fu, Zhiqi Shen, Jing Jih Chin, Hao Wang
Analyzing and reconstructing visual stimuli from brain signals effectively advances understanding of the human visual system. However, the EEG signals are complex and contain a amount of noise. This leads to substantial limitations in existing works of visual stimuli reconstruction from EEG, such as difficulties in aligning EEG embeddings with the fine-grained semantic information and a heavy reliance on additional large self-collected dataset for training. To address these challenges, we propose a novel approach called BrainVis. Firstly, we divide the EEG signals into various units and apply a self-supervised approach on them to obtain EEG time-domain features, in an attempt to ease the training difficulty. Additionally, we also propose to utilize the frequency-domain features to enhance the EEG representations. Then, we simultaneously align EEG time-frequency embeddings with the interpolation of the coarse and fine-grained semantics in the CLIP space, to highlight the primary visual components and reduce the cross-modal alignment difficulty. Finally, we adopt the cascaded diffusion models to reconstruct images. Our proposed BrainVis outperforms state of the arts in both semantic fidelity reconstruction and generation quality. Notably, we reduce the training data scale to 10% of the previous work.
Authors: Yevgeniy Men, Jonathan Fhima, Leo Anthony Celi, Lucas Zago Ribeiro, Luis Filipe Nakayama, Joachim A. Behar
Diabetic retinopathy (DR) is a prevalent complication of diabetes associated with a significant risk of vision loss. Timely identification is critical to curb vision impairment. Algorithms for DR staging from digital fundus images (DFIs) have been recently proposed. However, models often fail to generalize due to distribution shifts between the source domain on which the model was trained and the target domain where it is deployed. A common and particularly challenging shift is often encountered when the source- and target-domain supports do not fully overlap. In this research, we introduce DRStageNet, a deep learning model designed to mitigate this challenge. We used seven publicly available datasets, comprising a total of 93,534 DFIs that cover a variety of patient demographics, ethnicities, geographic origins and comorbidities. We fine-tune DINOv2, a pretrained model of self-supervised vision transformer, and implement a multi-source domain fine-tuning strategy to enhance generalization performance. We benchmark and demonstrate the superiority of our method to two state-of-the-art benchmarks, including a recently published foundation model. We adapted the grad-rollout method to our regression task in order to provide high-resolution explainability heatmaps. The error analysis showed that 59\% of the main errors had incorrect reference labels. DRStageNet is accessible at URL [upon acceptance of the manuscript].
Authors: Mohsen Gholami, Rabab Ward, Z. Jane Wang
This paper proposes an end-to-end framework for generating 3D human pose datasets using Neural Radiance Fields (NeRF). Public datasets generally have limited diversity in terms of human poses and camera viewpoints, largely due to the resource-intensive nature of collecting 3D human pose data. As a result, pose estimators trained on public datasets significantly underperform when applied to unseen out-of-distribution samples. Previous works proposed augmenting public datasets by generating 2D-3D pose pairs or rendering a large amount of random data. Such approaches either overlook image rendering or result in suboptimal datasets for pre-trained models. Here we propose PoseGen, which learns to generate a dataset (human 3D poses and images) with a feedback loss from a given pre-trained pose estimator. In contrast to prior art, our generated data is optimized to improve the robustness of the pre-trained model. The objective of PoseGen is to learn a distribution of data that maximizes the prediction error of a given pre-trained model. As the learned data distribution contains OOD samples of the pre-trained model, sampling data from such a distribution for further fine-tuning a pre-trained model improves the generalizability of the model. This is the first work that proposes NeRFs for 3D human data generation. NeRFs are data-driven and do not require 3D scans of humans. Therefore, using NeRF for data generation is a new direction for convenient user-specific data generation. Our extensive experiments show that the proposed PoseGen improves two baseline models (SPIN and HybrIK) on four datasets with an average 6% relative improvement.
Authors: James Gunn, Zygmunt Lenyk, Anuj Sharma, Andrea Donati, Alexandru Buburuzan, John Redford, Romain Mueller
Combining complementary sensor modalities is crucial to providing robust perception for safety-critical robotics applications such as autonomous driving (AD). Recent state-of-the-art camera-lidar fusion methods for AD rely on monocular depth estimation which is a notoriously difficult task compared to using depth information from the lidar directly. Here, we find that this approach does not leverage depth as expected and show that naively improving depth estimation does not lead to improvements in object detection performance and that, strikingly, removing depth estimation altogether does not degrade object detection performance. This suggests that relying on monocular depth could be an unnecessary architectural bottleneck during camera-lidar fusion. In this work, we introduce a novel fusion method that bypasses monocular depth estimation altogether and instead selects and fuses camera and lidar features in a bird's-eye-view grid using a simple attention mechanism. We show that our model can modulate its use of camera features based on the availability of lidar features and that it yields better 3D object detection on the nuScenes dataset than baselines relying on monocular depth estimation.
Authors: Riccardo Scodellaro, Ajinkya Kulkarni, Frauke Alves, Matthias Schröter
The recent successes in analyzing images with deep neural networks are almost exclusively achieved with Convolutional Neural Networks (CNNs). The training of these CNNs, and in fact of all deep neural network architectures, uses the backpropagation algorithm where the output of the network is compared with the desired result and the difference is then used to tune the weights of the network towards the desired outcome. In a 2022 preprint, Geoffrey Hinton suggested an alternative way of training which passes the desired results together with the images at the input of the network. This so called Forward Forward (FF) algorithm has up to now only been used in fully connected networks. In this paper, we show how the FF paradigm can be extended to CNNs. Our FF-trained CNN, featuring a novel spatially-extended labeling technique, achieves a classification accuracy of 99.0% on the MNIST hand-written digits dataset. We show how different hyperparameters affect the performance of the proposed algorithm and compare the results with CNN trained with the standard backpropagation approach. Furthermore, we use Class Activation Maps to investigate which type of features are learnt by the FF algorithm.
Authors: Soshi Shimada, Franziska Mueller, Jan Bednarik, Bardia Doosti, Bernd Bickel, Danhang Tang, Vladislav Golyanik, Jonathan Taylor, Christian Theobalt, Thabo Beeler
The physical properties of an object, such as mass, significantly affect how we manipulate it with our hands. Surprisingly, this aspect has so far been neglected in prior work on 3D motion synthesis. To improve the naturalness of the synthesized 3D hand object motions, this work proposes MACS the first MAss Conditioned 3D hand and object motion Synthesis approach. Our approach is based on cascaded diffusion models and generates interactions that plausibly adjust based on the object mass and interaction type. MACS also accepts a manually drawn 3D object trajectory as input and synthesizes the natural 3D hand motions conditioned by the object mass. This flexibility enables MACS to be used for various downstream applications, such as generating synthetic training data for ML tasks, fast animation of hands for graphics workflows, and generating character interactions for computer games. We show experimentally that a small-scale dataset is sufficient for MACS to reasonably generalize across interpolated and extrapolated object masses unseen during the training. Furthermore, MACS shows moderate generalization to unseen objects, thanks to the mass-conditioned contact labels generated by our surface contact synthesis model ConNet. Our comprehensive user study confirms that the synthesized 3D hand-object interactions are highly plausible and realistic.
Authors: Mohamed Adel Musallam, Vincent Gaudillière, Djamila Aouada
Visual place recognition is a key to unlocking spatial navigation for animals, humans and robots. While state-of-the-art approaches are trained in a supervised manner and therefore hardly capture the information needed for generalizing to unusual conditions, we argue that self-supervised learning may help abstracting the place representation so that it can be foreseen, irrespective of the conditions. More precisely, in this paper, we investigate learning features that are robust to appearance modifications while sensitive to geometric transformations in a self-supervised manner. This dual-purpose training is made possible by combining the two self-supervision main paradigms, \textit{i.e.} contrastive and predictive learning. Our results on standard benchmarks reveal that jointly learning such appearance-robust and geometry-sensitive image descriptors leads to competitive visual place recognition results across adverse seasonal and illumination conditions, without requiring any human-annotated labels.
Authors: Zimin Xia, Olaf Booij, Julian F. P. Kooij
We propose a novel end-to-end method for cross-view pose estimation. Given a ground-level query image and an aerial image that covers the query's local neighborhood, the 3 Degrees-of-Freedom camera pose of the query is estimated by matching its image descriptor to descriptors of local regions within the aerial image. The orientation-aware descriptors are obtained by using a translationally equivariant convolutional ground image encoder and contrastive learning. The Localization Decoder produces a dense probability distribution in a coarse-to-fine manner with a novel Localization Matching Upsampling module. A smaller Orientation Decoder produces a vector field to condition the orientation estimate on the localization. Our method is validated on the VIGOR and KITTI datasets, where it surpasses the state-of-the-art baseline by 72% and 36% in median localization error for comparable orientation estimation accuracy. The predicted probability distribution can represent localization ambiguity, and enables rejecting possible erroneous predictions. Without re-training, the model can infer on ground images with different field of views and utilize orientation priors if available. On the Oxford RobotCar dataset, our method can reliably estimate the ego-vehicle's pose over time, achieving a median localization error under 1 meter and a median orientation error of around 1 degree at 14 FPS.
Authors: Han Liang, Wenqian Zhang, Wenxuan Li, Jingyi Yu, Lan Xu
We have recently seen tremendous progress in diffusion advances for generating realistic human motions. Yet, they largely disregard the multi-human interactions. In this paper, we present InterGen, an effective diffusion-based approach that incorporates human-to-human interactions into the motion diffusion process, which enables layman users to customize high-quality two-person interaction motions, with only text guidance. We first contribute a multimodal dataset, named InterHuman. It consists of about 107M frames for diverse two-person interactions, with accurate skeletal motions and 23,337 natural language descriptions. For the algorithm side, we carefully tailor the motion diffusion model to our two-person interaction setting. To handle the symmetry of human identities during interactions, we propose two cooperative transformer-based denoisers that explicitly share weights, with a mutual attention mechanism to further connect the two denoising processes. Then, we propose a novel representation for motion input in our interaction diffusion model, which explicitly formulates the global relations between the two performers in the world frame. We further introduce two novel regularization terms to encode spatial relations, equipped with a corresponding damping scheme during the training of our interaction diffusion model. Extensive experiments validate the effectiveness and generalizability of InterGen. Notably, it can generate more diverse and compelling two-person motions than previous methods and enables various downstream applications for human interactions.
Authors: Pierre Marza, Laetitia Matignon, Olivier Simonin, Dhruv Batra, Christian Wolf, Devendra Singh Chaplot
Implicit representations such as Neural Radiance Fields (NeRF) have been shown to be very effective at novel view synthesis. However, these models typically require manual and careful human data collection for training. In this paper, we present AutoNeRF, a method to collect data required to train NeRFs using autonomous embodied agents. Our method allows an agent to explore an unseen environment efficiently and use the experience to build an implicit map representation autonomously. We compare the impact of different exploration strategies including handcrafted frontier-based exploration, end-to-end and modular approaches composed of trained high-level planners and classical low-level path followers. We train these models with different reward functions tailored to this problem and evaluate the quality of the learned representations on four different downstream tasks: classical viewpoint rendering, map reconstruction, planning, and pose refinement. Empirical results show that NeRFs can be trained on actively collected data using just a single episode of experience in an unseen environment, and can be used for several downstream robotic tasks, and that modular trained exploration models outperform other classical and end-to-end baselines. Finally, we show that AutoNeRF can reconstruct large-scale scenes, and is thus a useful tool to perform scene-specific adaptation as the produced 3D environment models can be loaded into a simulator to fine-tune a policy of interest.
Authors: Suman Saha, Lukas Hoyer, Anton Obukhov, Dengxin Dai, Luc Van Gool
With autonomous industries on the rise, domain adaptation of the visual perception stack is an important research direction due to the cost savings promise. Much prior art was dedicated to domain-adaptive semantic segmentation in the synthetic-to-real context. Despite being a crucial output of the perception stack, panoptic segmentation has been largely overlooked by the domain adaptation community. Therefore, we revisit well-performing domain adaptation strategies from other fields, adapt them to panoptic segmentation, and show that they can effectively enhance panoptic domain adaptation. Further, we study the panoptic network design and propose a novel architecture (EDAPS) designed explicitly for domain-adaptive panoptic segmentation. It uses a shared, domain-robust transformer encoder to facilitate the joint adaptation of semantic and instance features, but task-specific decoders tailored for the specific requirements of both domain-adaptive semantic and instance segmentation. As a result, the performance gap seen in challenging panoptic benchmarks is substantially narrowed. EDAPS significantly improves the state-of-the-art performance for panoptic segmentation UDA by a large margin of 20% on SYNTHIA-to-Cityscapes and even 72% on the more challenging SYNTHIA-to-Mapillary Vistas. The implementation is available at https://github.com/susaha/edaps.
Authors: Xinyang Huang, Chuang Zhu, Wenkai Chen
In semi-supervised domain adaptation (SSDA), a few labeled target samples of each class help the model to transfer knowledge representation from the fully labeled source domain to the target domain. Many existing methods ignore the benefits of making full use of the labeled target samples from multi-level. To make better use of this additional data, we propose a novel Prototype-based Multi-level Learning (ProML) framework to better tap the potential of labeled target samples. To achieve intra-domain adaptation, we first introduce a pseudo-label aggregation based on the intra-domain optimal transport to help the model align the feature distribution of unlabeled target samples and the prototype. At the inter-domain level, we propose a cross-domain alignment loss to help the model use the target prototype for cross-domain knowledge transfer. We further propose a dual consistency based on prototype similarity and linear classifier to promote discriminative learning of compact target feature representation at the batch level. Extensive experiments on three datasets, including DomainNet, VisDA2017, and Office-Home demonstrate that our proposed method achieves state-of-the-art performance in SSDA.
Authors: Georg Siedel, Weijia Shao, Silvia Vock, Andrey Morozov
Robustness is a fundamental property of machine learning classifiers required to achieve safety and reliability. In the field of adversarial robustness of image classifiers, robustness is commonly defined as the stability of a model to all input changes within a p-norm distance. However, in the field of random corruption robustness, variations observed in the real world are used, while p-norm corruptions are rarely considered. This study investigates the use of random p-norm corruptions to augment the training and test data of image classifiers. We evaluate the model robustness against imperceptible random p-norm corruptions and propose a novel robustness metric. We empirically investigate whether robustness transfers across different p-norms and derive conclusions on which p-norm corruptions a model should be trained and evaluated. We find that training data augmentation with a combination of p-norm corruptions significantly improves corruption robustness, even on top of state-of-the-art data augmentation schemes.
Authors: Christos Sakaridis, David Bruggemann, Fisher Yu, Luc Van Gool
Adaptation of semantic segmentation networks to different visual conditions is vital for robust perception in autonomous cars and robots. However, previous work has shown that most feature-level adaptation methods, which employ adversarial training and are validated on synthetic-to-real adaptation, provide marginal gains in condition-level adaptation, being outperformed by simple pixel-level adaptation via stylization. Motivated by these findings, we propose to leverage stylization in performing feature-level adaptation by aligning the internal network features extracted by the encoder of the network from the original and the stylized view of each input image with a novel feature invariance loss. In this way, we encourage the encoder to extract features that are already invariant to the style of the input, allowing the decoder to focus on parsing these features and not on further abstracting from the specific style of the input. We implement our method, named Condition-Invariant Semantic Segmentation (CISS), on the current state-of-the-art domain adaptation architecture and achieve outstanding results on condition-level adaptation. In particular, CISS sets the new state of the art in the popular daytime-to-nighttime Cityscapes$\to$Dark Zurich benchmark. Furthermore, our method achieves the second-best performance on the normal-to-adverse Cityscapes$\to$ACDC benchmark. CISS is shown to generalize well to domains unseen during training, such as BDD100K-night. Code is publicly available at https://github.com/SysCV/CISS .
Authors: Afifa Khaled, Ahmed A. Mubarak, Kun He
Recent deep learning models have attracted substantial attention in infant brain analysis. These models have performed state-of-the-art performance, such as semi-supervised techniques (e.g., Temporal Ensembling, mean teacher). However, these models depend on an encoder-decoder structure with stacked local operators to gather long-range information, and the local operators limit the efficiency and effectiveness. Besides, the $MRI$ data contain different tissue properties ($TPs$) such as $T1$ and $T2$. One major limitation of these models is that they use both data as inputs to the segment process, i.e., the models are trained on the dataset once, and it requires much computational and memory requirements during inference. In this work, we address the above limitations by designing a new deep-learning model, called 3D-DenseUNet, which works as adaptable global aggregation blocks in down-sampling to solve the issue of spatial information loss. The self-attention module connects the down-sampling blocks to up-sampling blocks, and integrates the feature maps in three dimensions of spatial and channel, effectively improving the representation potential and discriminating ability of the model. Additionally, we propose a new method called Two Independent Teachers ($2IT$), that summarizes the model weights instead of label predictions. Each teacher model is trained on different types of brain data, $T1$ and $T2$, respectively. Then, a fuse model is added to improve test accuracy and enable training with fewer parameters and labels compared to the Temporal Ensembling method without modifying the network architecture. Empirical results demonstrate the effectiveness of the proposed method. The code is available at https://github.com/AfifaKhaled/Two-Independent-Teachers-are-Better-Role-Model.
Authors: Deng Yu, Manfred Lau, Lin Gao, Hongbo Fu
We present a novel freehand sketch beautification method, which takes as input a freely drawn sketch of a man-made object and automatically beautifies it both geometrically and structurally. Beautifying a sketch is challenging because of its highly abstract and heavily diverse drawing manner. Existing methods are usually confined to the distribution of their limited training samples and thus cannot beautify freely drawn sketches with rich variations. To address this challenge, we adopt a divide-and-combine strategy. Specifically, we first parse an input sketch into semantic components, beautify individual components by a learned part beautification module based on part-level implicit manifolds, and then reassemble the beautified components through a structure beautification module. With this strategy, our method can go beyond the training samples and handle novel freehand sketches. We demonstrate the effectiveness of our system with extensive experiments and a perceptive study.
Authors: Yinghua Gao, Yiming Li, Xueluan Gong, Zhifeng Li, Shu-Tao Xia, Qian Wang
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where the adversary manipulates a small portion of training data such that the victim model predicts normally on the benign samples but classifies the triggered samples as the target class. The backdoor attack is an emerging yet threatening training-phase threat, leading to serious risks in DNN-based applications. In this paper, we revisit the trigger patterns of existing backdoor attacks. We reveal that they are either visible or not sparse and therefore are not stealthy enough. More importantly, it is not feasible to simply combine existing methods to design an effective sparse and invisible backdoor attack. To address this problem, we formulate the trigger generation as a bi-level optimization problem with sparsity and invisibility constraints and propose an effective method to solve it. The proposed method is dubbed sparse and invisible backdoor attack (SIBA). We conduct extensive experiments on benchmark datasets under different settings, which verify the effectiveness of our attack and its resistance to existing backdoor defenses. The codes for reproducing main experiments are available at \url{https://github.com/YinghuaGao/SIBA}.
Authors: Xiang 'Anthony' Chen, Jeff Burke, Ruofei Du, Matthew K. Hong, Jennifer Jacobs, Philippe Laban, Dingzeyu Li, Nanyun Peng, Karl D. D. Willis, Chien-Sheng Wu, Bolei Zhou
Through iterative, cross-disciplinary discussions, we define and propose next-steps for Human-centered Generative AI (HGAI). We contribute a comprehensive research agenda that lays out future directions of Generative AI spanning three levels: aligning with human values; assimilating human intents; and augmenting human abilities. By identifying these next-steps, we intend to draw interdisciplinary research teams to pursue a coherent set of emergent ideas in HGAI, focusing on their interested topics while maintaining a coherent big picture of the future work landscape.
Authors: Simon Doll, Niklas Hanselmann, Lukas Schneider, Richard Schulz, Markus Enzweiler, Hendrik P.A. Lensch
Following the tracking-by-attention paradigm, this paper introduces an object-centric, transformer-based framework for tracking in 3D. Traditional model-based tracking approaches incorporate the geometric effect of object- and ego motion between frames with a geometric motion model. Inspired by this, we propose S.T.A.R.-Track, which uses a novel latent motion model (LMM) to additionally adjust object queries to account for changes in viewing direction and lighting conditions directly in the latent space, while still modeling the geometric motion explicitly. Combined with a novel learnable track embedding that aids in modeling the existence probability of tracks, this results in a generic tracking framework that can be integrated with any query-based detector. Extensive experiments on the nuScenes benchmark demonstrate the benefits of our approach, showing \ac{sota} performance for DETR3D-based trackers while drastically reducing the number of identity switches of tracks at the same time.
Authors: Mustafa Shukor, Corentin Dancette, Alexandre Rame, Matthieu Cord
Large Language Models (LLMs) have made the ambitious quest for generalist agents significantly far from being a fantasy. A key hurdle for building such general models is the diversity and heterogeneity of tasks and modalities. A promising solution is unification, allowing the support of a myriad of tasks and modalities within one unified framework. While few large models (e.g., Flamingo (Alayrac et al., 2022), trained on massive datasets, can support more than two modalities, current small to mid-scale unified models are still limited to 2 modalities, usually image-text or video-text. The question that we ask is: is it possible to build efficiently a unified model that can support all modalities? To answer this, we propose UnIVAL, a step further towards this ambitious goal. Without relying on fancy datasets sizes or models with billions of parameters, the ~ 0.25B parameter UnIVAL model goes beyond two modalities and unifies text, images, video, and audio into a single model. Our model is efficiently pretrained on many tasks, based on task balancing and multimodal curriculum learning. UnIVAL shows competitive performance to existing state-of-the-art approaches, across image and video-text tasks. The feature representations learned from image and video-text modalities, allows the model to achieve competitive performance when finetuned on audio-text tasks, despite not being pretrained on audio. Thanks to the unified model, we propose a novel study on multimodal model merging via weight interpolation of models trained on different multimodal tasks, showing their benefits in particular for out-of-distribution generalization. Finally, we motivate unification by showing the synergy between tasks. The model weights and code are released here: https://github.com/mshukor/UnIVAL.
Authors: Ziyin Zhang, Ning Lu, Minghui Liao, Yongshuai Huang, Cheng Li, Min Wang, Wei Peng
Text recognition methods are gaining rapid development. Some advanced techniques, e.g., powerful modules, language models, and un- and semi-supervised learning schemes, consecutively push the performance on public benchmarks forward. However, the problem of how to better optimize a text recognition model from the perspective of loss functions is largely overlooked. CTC-based methods, widely used in practice due to their good balance between performance and inference speed, still grapple with accuracy degradation. This is because CTC loss emphasizes the optimization of the entire sequence target while neglecting to learn individual characters. We propose a self-distillation scheme for CTC-based model to address this issue. It incorporates a framewise regularization term in CTC loss to emphasize individual supervision, and leverages the maximizing-a-posteriori of latent alignment to solve the inconsistency problem that arises in distillation between CTC-based models. We refer to the regularized CTC loss as Distillation Connectionist Temporal Classification (DCTC) loss. DCTC loss is module-free, requiring no extra parameters, longer inference lag, or additional training data or phases. Extensive experiments on public benchmarks demonstrate that DCTC can boost text recognition model accuracy by up to 2.6%, without any of these drawbacks.
Authors: Yicheng Chen, Shengxiang Ji, Yuelin Xin, Kun Han, Xiaohui Xie
This research explores a novel approach in the realm of learning-based image registration, addressing the limitations inherent in weakly-supervised and unsupervised methods. Weakly-supervised techniques depend heavily on scarce labeled data, while unsupervised strategies rely on indirect measures of accuracy through image similarity. Notably, traditional supervised learning is not utilized due to the lack of precise deformation ground-truth in medical imaging. Our study introduces a unique training framework with On-the-Fly Guidance (OFG) to enhance existing models. This framework, during training, generates pseudo-ground truth a few steps ahead by refining the current deformation prediction with our custom optimizer. This pseudo-ground truth then serves to directly supervise the model in a supervised learning context. The process involves optimizing the predicted deformation with a limited number of steps, ensuring training efficiency and setting achievable goals for each training phase. OFG notably boosts the precision of existing image registration techniques while maintaining the speed of learning-based methods. We assessed our approach using various pseudo-ground truth generation strategies, including predictions and optimized outputs from established registration models. Our experiments spanned three benchmark datasets and three cutting-edge models, with OFG demonstrating significant and consistent enhancements, surpassing previous state-of-the-arts in the field. OFG offers an easily integrable plug-and-play solution to enhance the training effectiveness of learning-based image registration models. Code at https://github.com/miraclefactory/on-the-fly-guidance.
Authors: Mariona Carós, Ariadna Just, Santi Seguí, Jordi Vitrià
Airborne LiDAR systems have the capability to capture the Earth's surface by generating extensive point cloud data comprised of points mainly defined by 3D coordinates. However, labeling such points for supervised learning tasks is time-consuming. As a result, there is a need to investigate techniques that can learn from unlabeled data to significantly reduce the number of annotated samples. In this work, we propose to train a self-supervised encoder with Barlow Twins and use it as a pre-trained network in the task of semantic scene segmentation. The experimental results demonstrate that our unsupervised pre-training boosts performance once fine-tuned on the supervised task, especially for under-represented categories.
Authors: Christoph Reich, Biplob Debnath, Deep Patel, Srimat Chakradhar
JPEG remains one of the most widespread lossy image coding methods. However, the non-differentiable nature of JPEG restricts the application in deep learning pipelines. Several differentiable approximations of JPEG have recently been proposed to address this issue. This paper conducts a comprehensive review of existing diff. JPEG approaches and identifies critical details that have been missed by previous methods. To this end, we propose a novel diff. JPEG approach, overcoming previous limitations. Our approach is differentiable w.r.t. the input image, the JPEG quality, the quantization tables, and the color conversion parameters. We evaluate the forward and backward performance of our diff. JPEG approach against existing methods. Additionally, extensive ablations are performed to evaluate crucial design choices. Our proposed diff. JPEG resembles the (non-diff.) reference implementation best, significantly surpassing the recent-best diff. approach by $3.47$dB (PSNR) on average. For strong compression rates, we can even improve PSNR by $9.51$dB. Strong adversarial attack results are yielded by our diff. JPEG, demonstrating the effective gradient approximation. Our code is available at https://github.com/necla-ml/Diff-JPEG.
Authors: Hao Li, Jingkuan Song, Lianli Gao, Xiaosu Zhu, Heng Tao Shen
Cross-modal Retrieval methods build similarity relations between vision and language modalities by jointly learning a common representation space. However, the predictions are often unreliable due to the Aleatoric uncertainty, which is induced by low-quality data, e.g., corrupt images, fast-paced videos, and non-detailed texts. In this paper, we propose a novel Prototype-based Aleatoric Uncertainty Quantification (PAU) framework to provide trustworthy predictions by quantifying the uncertainty arisen from the inherent data ambiguity. Concretely, we first construct a set of various learnable prototypes for each modality to represent the entire semantics subspace. Then Dempster-Shafer Theory and Subjective Logic Theory are utilized to build an evidential theoretical framework by associating evidence with Dirichlet Distribution parameters. The PAU model induces accurate uncertainty and reliable predictions for cross-modal retrieval. Extensive experiments are performed on four major benchmark datasets of MSR-VTT, MSVD, DiDeMo, and MS-COCO, demonstrating the effectiveness of our method. The code is accessible at https://github.com/leolee99/PAU.
Authors: Giuseppe Stragapede, Ruben Vera-Rodriguez, Ruben Tolosana, Aythami Morales, Naser Damer, Julian Fierrez, Javier Ortega-Garcia
Analyzing keystroke dynamics (KD) for biometric verification has several advantages: it is among the most discriminative behavioral traits; keyboards are among the most common human-computer interfaces, being the primary means for users to enter textual data; its acquisition does not require additional hardware, and its processing is relatively lightweight; and it allows for transparently recognizing subjects. However, the heterogeneity of experimental protocols and metrics, and the limited size of the databases adopted in the literature impede direct comparisons between different systems, thus representing an obstacle in the advancement of keystroke biometrics. To alleviate this aspect, we present a new experimental framework to benchmark KD-based biometric verification performance and fairness based on tweet-long sequences of variable transcript text from over 185,000 subjects, acquired through desktop and mobile keyboards, extracted from the Aalto Keystroke Databases. The framework runs on CodaLab in the form of the Keystroke Verification Challenge (KVC). Moreover, we also introduce a novel fairness metric, the Skewed Impostor Ratio (SIR), to capture inter- and intra-demographic group bias patterns in the verification scores. We demonstrate the usefulness of the proposed framework by employing two state-of-the-art keystroke verification systems, TypeNet and TypeFormer, to compare different sets of input features, achieving a less privacy-invasive system, by discarding the analysis of text content (ASCII codes of the keys pressed) in favor of extended features in the time domain. Our experiments show that this approach allows to maintain satisfactory performance.
Authors: Wenhao Tang, Junding Sun, Shuihua Wang, Yudong Zhang
In recent years, the rapid development of deep learning has led to a wide range of applications in the field of medical image classification. The variants of neural network models with ever-increasing performance share some commonalities: to try to mitigate overfitting, improve generalization, avoid gradient vanishing and exploding, etc. AlexNet first utilizes the dropout technique to mitigate overfitting and the ReLU activation function to avoid gradient vanishing. Therefore, we focus our discussion on AlexNet, which has contributed greatly to the development of CNNs in 2012. After reviewing over 40 papers, including journal papers and conference papers, we give a narrative on the technical details, advantages, and application areas of AlexNet.
Authors: Chihiro Noguchi, Shun Fukuda, Masao Yamanaka
Scene Text Image Super-resolution (STISR) has recently achieved great success as a preprocessing method for scene text recognition. STISR aims to transform blurred and noisy low-resolution (LR) text images in real-world settings into clear high-resolution (HR) text images suitable for scene text recognition. In this study, we leverage text-conditional diffusion models (DMs), known for their impressive text-to-image synthesis capabilities, for STISR tasks. Our experimental results revealed that text-conditional DMs notably surpass existing STISR methods. Especially when texts from LR text images are given as input, the text-conditional DMs are able to produce superior quality super-resolution text images. Utilizing this capability, we propose a novel framework for synthesizing LR-HR paired text image datasets. This framework consists of three specialized text-conditional DMs, each dedicated to text image synthesis, super-resolution, and image degradation. These three modules are vital for synthesizing distinct LR and HR paired images, which are more suitable for training STISR methods. Our experiments confirmed that these synthesized image pairs significantly enhance the performance of STISR methods in the TextZoom evaluation.
Authors: Xin Zhang, Jiawei Du, Yunsong Li, Weiying Xie, Joey Tianyi Zhou
Dataset pruning aims to construct a coreset capable of achieving performance comparable to the original, full dataset. Most existing dataset pruning methods rely on snapshot-based criteria to identify representative samples, often resulting in poor generalization across various pruning and cross-architecture scenarios. Recent studies have addressed this issue by expanding the scope of training dynamics considered, including factors such as forgetting event and probability change, typically using an averaging approach. However, these works struggle to integrate a broader range of training dynamics without overlooking well-generalized samples, which may not be sufficiently highlighted in an averaging manner. In this study, we propose a novel dataset pruning method termed as Temporal Dual-Depth Scoring (TDDS), to tackle this problem. TDDS utilizes a dual-depth strategy to achieve a balance between incorporating extensive training dynamics and identifying representative samples for dataset pruning. In the first depth, we estimate the series of each sample's individual contributions spanning the training progress, ensuring comprehensive integration of training dynamics. In the second depth, we focus on the variability of the sample-wise contributions identified in the first depth to highlight well-generalized samples. Extensive experiments conducted on CIFAR and ImageNet datasets verify the superiority of TDDS over previous SOTA methods. Specifically on CIFAR-100, our method achieves 54.51% accuracy with only 10% training data, surpassing random selection by 7.83% and other comparison methods by at least 12.69%.
Authors: Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, Cong Wei, Botao Yu, Ruibin Yuan, Renliang Sun, Ming Yin, Boyuan Zheng, Zhenzhu Yang, Yibo Liu, Wenhao Huang, Huan Sun, Yu Su, Wenhu Chen
We introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU includes 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering. These questions span 30 subjects and 183 subfields, comprising 30 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures. Unlike existing benchmarks, MMMU focuses on advanced perception and reasoning with domain-specific knowledge, challenging models to perform tasks akin to those faced by experts. The evaluation of 14 open-source LMMs as well as the proprietary GPT-4V(ision) and Gemini highlights the substantial challenges posed by MMMU. Even the advanced GPT-4V and Gemini Ultra only achieve accuracies of 56% and 59% respectively, indicating significant room for improvement. We believe MMMU will stimulate the community to build next-generation multimodal foundation models towards expert artificial general intelligence.
Authors: Jay C. Rothenberger, Dimitrios I. Diochnos
In many practical computer vision scenarios unlabeled data is plentiful, but labels are scarce and difficult to obtain. As a result, semi-supervised learning which leverages unlabeled data to boost the performance of supervised classifiers have received significant attention in recent literature. One major class of semi-supervised algorithms is co-training. In co-training two different models leverage different independent and sufficient "views" of the data to jointly make better predictions. During co-training each model creates pseudo labels on unlabeled points which are used to improve the other model. We show that in the common case when independent views are not available we can construct such views inexpensively using pre-trained models. Co-training on the constructed views yields a performance improvement over any of the individual views we construct and performance comparable with recent approaches in semi-supervised learning, but has some undesirable properties. To alleviate the issues present with co-training we present Meta Co-Training which is an extension of the successful Meta Pseudo Labels approach to two views. Our method achieves new state-of-the-art performance on ImageNet-10% with very few training resources, as well as outperforming prior semi-supervised work on several other fine-grained image classification datasets.
Authors: Christian Weihsbach, Christian N. Kruse, Alexander Bigalke, Mattias P. Heinrich
Applying pre-trained medical segmentation models on out-of-domain images often yields predictions of insufficient quality. Several strategies have been proposed to maintain model performance, such as finetuning or unsupervised- and source-free domain adaptation. These strategies set restrictive requirements for data availability. In this study, we propose to combine domain generalization and test-time adaptation to create a highly effective approach for reusing pre-trained models in unseen target domains. Domain-generalized pre-training on source data is used to obtain the best initial performance in the target domain. We introduce the MIND descriptor previously used in image registration tasks as a further technique to achieve generalization and present superior performance for small-scale datasets compared to existing approaches. At test-time, high-quality segmentation for every single unseen scan is ensured by optimizing the model weights for consistency given different image augmentations. That way, our method enables separate use of source and target data and thus removes current data availability barriers. Moreover, the presented method is highly modular as it does not require specific model architectures or prior knowledge of involved domains and labels. We demonstrate this by integrating it into the nnUNet, which is currently the most popular and accurate framework for medical image segmentation. We employ multiple datasets covering abdominal, cardiac, and lumbar spine scans and compose several out-of-domain scenarios in this study. We demonstrate that our method, combined with pre-trained whole-body CT models, can effectively segment MR images with high accuracy in all of the aforementioned scenarios. Open-source code can be found here: https://github.com/multimodallearning/DG-TTA
Authors: Mike Ranzinger, Greg Heinrich, Jan Kautz, Pavlo Molchanov
A handful of visual foundation models (VFMs) have recently emerged as the backbones for numerous downstream tasks. VFMs like CLIP, DINOv2, SAM are trained with distinct objectives, exhibiting unique characteristics for various downstream tasks. We find that despite their conceptual differences, these models can be effectively merged into a unified model through multi-teacher distillation. We name this approach AM-RADIO (Agglomerative Model -- Reduce All Domains Into One). This integrative approach not only surpasses the performance of individual teacher models but also amalgamates their distinctive features, such as zero-shot vision-language comprehension, detailed pixel-level understanding, and open vocabulary segmentation capabilities. In pursuit of the most hardware-efficient backbone, we evaluated numerous architectures in our multi-teacher distillation pipeline using the same training recipe. This led to the development of a novel architecture (E-RADIO) that exceeds the performance of its predecessors and is at least 7x faster than the teacher models. Our comprehensive benchmarking process covers downstream tasks including ImageNet classification, ADE20k semantic segmentation, COCO object detection and LLaVa-1.5 framework.
Code: https://github.com/NVlabs/RADIO
Authors: Soham Bafana
Understanding object recognition patterns in mice is crucial for advancing behavioral neuroscience and has significant implications for human health, particularly in the realm of Alzheimer's research. This study is centered on the development, application, and evaluation of a state-of-the-art computational pipeline designed to analyze such behaviors, specifically focusing on Novel Object Recognition (NOR) and Spontaneous Location Recognition (SLR) tasks. The pipeline integrates three advanced computational models: Any-Maze for initial data collection, DeepLabCut for detailed pose estimation, and Convolutional Neural Networks (CNNs) for nuanced behavioral classification. Employed across four distinct mouse groups, this pipeline demonstrated high levels of accuracy and robustness. Despite certain challenges like video quality limitations and the need for manual calculations, the results affirm the pipeline's efficacy and potential for scalability. The study serves as a proof of concept for a multidimensional computational approach to behavioral neuroscience, emphasizing the pipeline's versatility and readiness for future, more complex analyses.
Authors: Ilektra Karasante, Lazaro Alonso, Ioannis Prapas, Akanksha Ahuja, Nuno Carvalhais, Ioannis Papoutsis
The global occurrence, scale, and frequency of wildfires pose significant threats to ecosystem services and human livelihoods. To effectively quantify and attribute the antecedent conditions for wildfires, a thorough understanding of Earth system dynamics is imperative. In response, we introduce the SeasFire datacube, a meticulously curated spatiotemporal dataset tailored for global sub-seasonal to seasonal wildfire modeling via Earth observation. The SeasFire datacube comprises of 59 variables encompassing climate, vegetation, oceanic indices, and human factors, has an 8-day temporal resolution and a spatial resolution of 0.25$^{\circ}$, and spans from 2001 to 2021. We showcase the versatility of SeasFire for exploring the variability and seasonality of wildfire drivers, modeling causal links between ocean-climate teleconnections and wildfires, and predicting sub-seasonal wildfire patterns across multiple timescales with a Deep Learning model. We publicly release the SeasFire datacube and appeal to Earth system scientists and Machine Learning practitioners to use it for an improved understanding and anticipation of wildfires.
Authors: Shuyang Sun, Runjia Li, Philip Torr, Xiuye Gu, Siyang Li
Existing open-vocabulary image segmentation methods require a fine-tuning step on mask annotations and/or image-text datasets. Mask labels are labor-intensive, which limits the number of categories in segmentation datasets. As a result, the open-vocabulary capacity of pre-trained VLMs is severely reduced after fine-tuning. However, without fine-tuning, VLMs trained under weak image-text supervision tend to make suboptimal mask predictions when there are text queries referring to non-existing concepts in the image. To alleviate these issues, we introduce a novel recurrent framework that progressively filters out irrelevant texts and enhances mask quality without training efforts. The recurrent unit is a two-stage segmenter built upon a VLM with frozen weights. Thus, our model retains the VLM's broad vocabulary space and strengthens its segmentation capability. Experimental results show that our method outperforms not only the training-free counterparts, but also those fine-tuned with millions of additional data samples, and sets new state-of-the-art records for both zero-shot semantic and referring image segmentation tasks. Specifically, we improve the current record by 28.8, 16.0, and 6.9 mIoU on Pascal VOC, COCO Object, and Pascal Context.
Authors: Yufeng Liu
Nighttime unmanned aerial vehicle (UAV) tracking has been facilitated with indispensable plug-and-play low-light enhancers. However, the introduction of low-light enhancers increases the extra computational burden for the UAV, significantly hindering the development of real-time UAV applications. Meanwhile, these state-of-the-art (SOTA) enhancers lack tight coupling with the advanced daytime UAV tracking approach. To solve the above issues, this work proposes a novel mutual-learning knowledge distillation framework for nighttime UAV tracking, i.e., MLKD. This framework is constructed to learn a compact and fast nighttime tracker via knowledge transferring from the teacher and knowledge sharing among various students. Specifically, an advanced teacher based on a SOTA enhancer and a superior tracking backbone is adopted for guiding the student based only on the tight coupling-aware tracking backbone to directly extract nighttime object features. To address the biased learning of a single student, diverse lightweight students with different distillation methods are constructed to focus on various aspects of the teacher's knowledge. Moreover, an innovative mutual-learning room is designed to elect the superior student candidate to assist the remaining students frame-by-frame in the training phase. Furthermore, the final best student, i.e., MLKD-Track, is selected through the testing dataset. Extensive experiments demonstrate the effectiveness and superiority of MLKD and MLKD-Track. The practicality of the MLKD-Track is verified in real-world tests with different challenging situations. The code is available at https://github.com/lyfeng001/MLKD.
Authors: Wenyi Hong, Weihan Wang, Qingsong Lv, Jiazheng Xu, Wenmeng Yu, Junhui Ji, Yan Wang, Zihan Wang, Yuxuan Zhang, Juanzi Li, Bin Xu, Yuxiao Dong, Ming Ding, Jie Tang
People are spending an enormous amount of time on digital devices through graphical user interfaces (GUIs), e.g., computer or smartphone screens. Large language models (LLMs) such as ChatGPT can assist people in tasks like writing emails, but struggle to understand and interact with GUIs, thus limiting their potential to increase automation levels. In this paper, we introduce CogAgent, an 18-billion-parameter visual language model (VLM) specializing in GUI understanding and navigation. By utilizing both low-resolution and high-resolution image encoders, CogAgent supports input at a resolution of 1120*1120, enabling it to recognize tiny page elements and text. As a generalist visual language model, CogAgent achieves the state of the art on five text-rich and four general VQA benchmarks, including VQAv2, OK-VQA, Text-VQA, ST-VQA, ChartQA, infoVQA, DocVQA, MM-Vet, and POPE. CogAgent, using only screenshots as input, outperforms LLM-based methods that consume extracted HTML text on both PC and Android GUI navigation tasks -- Mind2Web and AITW, advancing the state of the art. The model and codes are available at https://github.com/THUDM/CogVLM .
Authors: Pietro Bonazzi, Julian Moosmann, Yawei Li, Sizhen Bian, Michele Magno
This paper addresses the growing interest in deploying deep learning models directly in-sensor. We present "Q-Segment", a quantized real-time segmentation algorithm, and conduct a comprehensive evaluation on a low-power edge vision platform with an in-sensors processor, the Sony IMX500. One of the main goals of the model is to achieve end-to-end image segmentation for vessel-based medical diagnosis. Deployed on the IMX500 platform, Q-Segment achieves ultra-low inference time in-sensor only 0.23 ms and power consumption of only 72mW. We compare the proposed network with state-of-the-art models, both float and quantized, demonstrating that the proposed solution outperforms existing networks on various platforms in computing efficiency, e.g., by a factor of 75x compared to ERFNet. The network employs an encoder-decoder structure with skip connections, and results in a binary accuracy of 97.25% and an Area Under the Receiver Operating Characteristic Curve (AUC) of 96.97% on the CHASE dataset. We also present a comparison of the IMX500 processing core with the Sony Spresense, a low-power multi-core ARM Cortex-M microcontroller, and a single-core ARM Cortex-M4 showing that it can achieve in-sensor processing with end-to-end low latency (17 ms) and power concumption (254mW). This research contributes valuable insights into edge-based image segmentation, laying the foundation for efficient algorithms tailored to low-power environments.
Authors: Yuming Qiu, Aleksandra Pizurica, Qi Ming, Nicolas Nadisic
Automated mark localization in scatter images, greatly helpful for discovering knowledge and understanding enormous document images and reasoning in visual question answering AI systems, is a highly challenging problem because of the ubiquity of overlapping marks. Locating overlapping marks faces many difficulties such as no texture, less contextual information, hallow shape and tiny size. Here, we formulate it as a combinatorial optimization problem on clustering-based re-visualization from a non-training generative perspective, to locate scatter marks by finding the status of multi-variables when an objective function reaches a minimum. The objective function is constructed on difference between binarized scatter images and corresponding generated re-visualization based on their clustering. Fundamentally, re-visualization tries to generate a new scatter graph only taking a rasterized scatter image as an input, and clustering is employed to provide the information for such re-visualization. This method could stably locate severely-overlapping, variable-size and variable-shape marks in scatter images without dependence of any training dataset or reference. Meanwhile, we propose an adaptive variant of simulated annealing which can works on various connected regions. In addition, we especially built a dataset named SML2023 containing hundreds of scatter images with different markers and various levels of overlapping severity, and tested the proposed method and compared it to existing methods. The results show that it can accurately locate most marks in scatter images with different overlapping severity and marker types, with about 0.3 absolute increase on an assignment-cost-based metric in comparison with state-of-the-art methods. This work is of value to data mining on massive web pages and literatures, and shedding new light on image measurement such as bubble counting.
Authors: Chien-Yu Lin, Qichen Fu, Thomas Merth, Karren Yang, Anurag Ranjan
Super-resolution (SR) techniques have recently been proposed to upscale the outputs of neural radiance fields (NeRF) and generate high-quality images with enhanced inference speeds. However, existing NeRF+SR methods increase training overhead by using extra input features, loss functions, and/or expensive training procedures such as knowledge distillation. In this paper, we aim to leverage SR for efficiency gains without costly training or architectural changes. Specifically, we build a simple NeRF+SR pipeline that directly combines existing modules, and we propose a lightweight augmentation technique, random patch sampling, for training. Compared to existing NeRF+SR methods, our pipeline mitigates the SR computing overhead and can be trained up to 23x faster, making it feasible to run on consumer devices such as the Apple MacBook. Experiments show our pipeline can upscale NeRF outputs by 2-4x while maintaining high quality, increasing inference speeds by up to 18x on an NVIDIA V100 GPU and 12.8x on an M1 Pro chip. We conclude that SR can be a simple but effective technique for improving the efficiency of NeRF models for consumer devices.
Authors: Fernando Pérez-García, Sam Bond-Taylor, Pedro P. Sanchez, Boris van Breugel, Daniel C. Castro, Harshita Sharma, Valentina Salvatelli, Maria T. A. Wetscherek, Hannah Richardson, Matthew P. Lungren, Aditya Nori, Javier Alvarez-Valle, Ozan Oktay, Maximilian Ilse
Biomedical imaging datasets are often small and biased, meaning that real-world performance of predictive models can be substantially lower than expected from internal testing. This work proposes using generative image editing to simulate dataset shifts and diagnose failure modes of biomedical vision models; this can be used in advance of deployment to assess readiness, potentially reducing cost and patient harm. Existing editing methods can produce undesirable changes, with spurious correlations learned due to the co-occurrence of disease and treatment interventions, limiting practical applicability. To address this, we train a text-to-image diffusion model on multiple chest X-ray datasets and introduce a new editing method RadEdit that uses multiple masks, if present, to constrain changes and ensure consistency in the edited images. We consider three types of dataset shifts: acquisition shift, manifestation shift, and population shift, and demonstrate that our approach can diagnose failures and quantify model robustness without additional data collection, complementing more qualitative tools for explainable AI.
Authors: Yuming Gu, You Xie, Hongyi Xu, Guoxian Song, Yichun Shi, Di Chang, Jing Yang, Linjie Luo
We present DiffPortrait3D, a conditional diffusion model that is capable of synthesizing 3D-consistent photo-realistic novel views from as few as a single in-the-wild portrait. Specifically, given a single RGB input, we aim to synthesize plausible but consistent facial details rendered from novel camera views with retained both identity and facial expression. In lieu of time-consuming optimization and fine-tuning, our zero-shot method generalizes well to arbitrary face portraits with unposed camera views, extreme facial expressions, and diverse artistic depictions. At its core, we leverage the generative prior of 2D diffusion models pre-trained on large-scale image datasets as our rendering backbone, while the denoising is guided with disentangled attentive control of appearance and camera pose. To achieve this, we first inject the appearance context from the reference image into the self-attention layers of the frozen UNets. The rendering view is then manipulated with a novel conditional control module that interprets the camera pose by watching a condition image of a crossed subject from the same view. Furthermore, we insert a trainable cross-view attention module to enhance view consistency, which is further strengthened with a novel 3D-aware noise generation process during inference. We demonstrate state-of-the-art results both qualitatively and quantitatively on our challenging in-the-wild and multi-view benchmarks.
Authors: Abdallah Dib, Luiz Gustavo Hafemann, Emeline Got, Trevor Anderson, Amin Fadaeinejad, Rafael M. O. Cruz, Marc-Andre Carbonneau
Reconstructing an avatar from a portrait image has many applications in multimedia, but remains a challenging research problem. Extracting reflectance maps and geometry from one image is ill-posed: recovering geometry is a one-to-many mapping problem and reflectance and light are difficult to disentangle. Accurate geometry and reflectance can be captured under the controlled conditions of a light stage, but it is costly to acquire large datasets in this fashion. Moreover, training solely with this type of data leads to poor generalization with in-the-wild images. This motivates the introduction of MoSAR, a method for 3D avatar generation from monocular images. We propose a semi-supervised training scheme that improves generalization by learning from both light stage and in-the-wild datasets. This is achieved using a novel differentiable shading formulation. We show that our approach effectively disentangles the intrinsic face parameters, producing relightable avatars. As a result, MoSAR estimates a richer set of skin reflectance maps, and generates more realistic avatars than existing state-of-the-art methods. We also introduce a new dataset, named FFHQ-UV-Intrinsics, the first public dataset providing intrinsic face attributes at scale (diffuse, specular, ambient occlusion and translucency maps) for a total of 10k subjects. The project website and the dataset are available on the following link: https://ubisoft-laforge.github.io/character/mosar/
Authors: Dongseob Kim, Seungho Lee, Junsuk Choe, Hyunjung Shim
State-of-the-art techniques in weakly-supervised semantic segmentation (WSSS) using image-level labels exhibit severe performance degradation on driving scene datasets such as Cityscapes. To address this challenge, we develop a new WSSS framework tailored to driving scene datasets. Based on extensive analysis of dataset characteristics, we employ Contrastive Language-Image Pre-training (CLIP) as our baseline to obtain pseudo-masks. However, CLIP introduces two key challenges: (1) pseudo-masks from CLIP lack in representing small object classes, and (2) these masks contain notable noise. We propose solutions for each issue as follows. (1) We devise Global-Local View Training that seamlessly incorporates small-scale patches during model training, thereby enhancing the model's capability to handle small-sized yet critical objects in driving scenes (e.g., traffic light). (2) We introduce Consistency-Aware Region Balancing (CARB), a novel technique that discerns reliable and noisy regions through evaluating the consistency between CLIP masks and segmentation predictions. It prioritizes reliable pixels over noisy pixels via adaptive loss weighting. Notably, the proposed method achieves 51.8\% mIoU on the Cityscapes test dataset, showcasing its potential as a strong WSSS baseline on driving scene datasets. Experimental results on CamVid and WildDash2 demonstrate the effectiveness of our method across diverse datasets, even with small-scale datasets or visually challenging conditions. The code is available at https://github.com/k0u-id/CARB.
Authors: Dawid Malarz, Weronika Smolak, Jacek Tabor, Sławomir Tadeja, Przemysław Spurek
Neural Radiance Fields (NeRFs) have demonstrated the remarkable potential of neural networks to capture the intricacies of 3D objects. By encoding the shape and color information within neural network weights, NeRFs excel at producing strikingly sharp novel views of 3D objects. Recently, numerous generalizations of NeRFs utilizing generative models have emerged, expanding its versatility. In contrast, Gaussian Splatting (GS) offers a similar renders quality with faster training and inference as it does not need neural networks to work. We encode information about the 3D objects in the set of Gaussian distributions that can be rendered in 3D similarly to classical meshes. Unfortunately, GS are difficult to condition since they usually require circa hundred thousand Gaussian components. To mitigate the caveats of both models, we propose a hybrid model that uses GS representation of the 3D object's shape and NeRF-based encoding of color and opacity. Our model uses Gaussian distributions with trainable positions (i.e. means of Gaussian), shape (i.e. covariance of Gaussian), color and opacity, and neural network, which takes parameters of Gaussian and viewing direction to produce changes in color and opacity. Consequently, our model better describes shadows, light reflections, and transparency of 3D objects.
Authors: Chi Zhang, Zhao Yang, Jiaxuan Liu, Yucheng Han, Xin Chen, Zebiao Huang, Bin Fu, Gang Yu
Recent advancements in large language models (LLMs) have led to the creation of intelligent agents capable of performing complex tasks. This paper introduces a novel LLM-based multimodal agent framework designed to operate smartphone applications. Our framework enables the agent to operate smartphone applications through a simplified action space, mimicking human-like interactions such as tapping and swiping. This novel approach bypasses the need for system back-end access, thereby broadening its applicability across diverse apps. Central to our agent's functionality is its innovative learning method. The agent learns to navigate and use new apps either through autonomous exploration or by observing human demonstrations. This process generates a knowledge base that the agent refers to for executing complex tasks across different applications. To demonstrate the practicality of our agent, we conducted extensive testing over 50 tasks in 10 different applications, including social media, email, maps, shopping, and sophisticated image editing tools. The results affirm our agent's proficiency in handling a diverse array of high-level tasks.
Authors: Xianfang Zeng, Xin Chen, Zhongqi Qi, Wen Liu, Zibo Zhao, Zhibin Wang, Bin Fu, Yong Liu, Gang Yu
This paper presents Paint3D, a novel coarse-to-fine generative framework that is capable of producing high-resolution, lighting-less, and diverse 2K UV texture maps for untextured 3D meshes conditioned on text or image inputs. The key challenge addressed is generating high-quality textures without embedded illumination information, which allows the textures to be re-lighted or re-edited within modern graphics pipelines. To achieve this, our method first leverages a pre-trained depth-aware 2D diffusion model to generate view-conditional images and perform multi-view texture fusion, producing an initial coarse texture map. However, as 2D models cannot fully represent 3D shapes and disable lighting effects, the coarse texture map exhibits incomplete areas and illumination artifacts. To resolve this, we train separate UV Inpainting and UVHD diffusion models specialized for the shape-aware refinement of incomplete areas and the removal of illumination artifacts. Through this coarse-to-fine process, Paint3D can produce high-quality 2K UV textures that maintain semantic consistency while being lighting-less, significantly advancing the state-of-the-art in texturing 3D objects.
Authors: Han Huang, Yulun Wu, Junsheng Zhou, Ge Gao, Ming Gu, Yu-Shen Liu
Recently, neural implicit functions have demonstrated remarkable results in the field of multi-view reconstruction. However, most existing methods are tailored for dense views and exhibit unsatisfactory performance when dealing with sparse views. Several latest methods have been proposed for generalizing implicit reconstruction to address the sparse view reconstruction task, but they still suffer from high training costs and are merely valid under carefully selected perspectives. In this paper, we propose a novel sparse view reconstruction framework that leverages on-surface priors to achieve highly faithful surface reconstruction. Specifically, we design several constraints on global geometry alignment and local geometry refinement for jointly optimizing coarse shapes and fine details. To achieve this, we train a neural network to learn a global implicit field from the on-surface points obtained from SfM and then leverage it as a coarse geometric constraint. To exploit local geometric consistency, we project on-surface points onto seen and unseen views, treating the consistent loss of projected features as a fine geometric constraint. The experimental results with DTU and BlendedMVS datasets in two prevalent sparse settings demonstrate significant improvements over the state-of-the-art methods.