Authors: Richard Schmit
Abstract: Detecting small objects remains a significant challenge in single-shot object detectors due to the inherent trade-off between spatial resolution and semantic richness in convolutional feature maps. To address this issue, we propose a novel framework that enables small object representations to "borrow" discriminative features from larger, semantically richer instances within the same class. Our architecture introduces three key components: the Feature Matching Block (FMB) to identify semantically similar descriptors across layers, the Feature Representing Block (FRB) to generate enhanced shallow features through weighted aggregation, and the Feature Fusion Block (FFB) to refine feature maps by integrating original, borrowed, and context information. Built upon the SSD framework, our method improves the descriptive capacity of shallow layers while maintaining real-time detection performance. Experimental results demonstrate that our approach significantly boosts small object detection accuracy over baseline methods, offering a promising direction for robust object detection in complex visual environments.
Authors: Vasudev Sharma, Ahmed Alagha, Abdelhakim Khellaf, Vincent Quoc-Huy Trinh, Mahdi S. Hosseini
Abstract: Vision-language models (VLMs) have gained significant attention in computational pathology due to their multimodal learning capabilities that enhance big-data analytics of giga-pixel whole slide image (WSI). However, their sensitivity to large-scale clinical data, task formulations, and prompt design remains an open question, particularly in terms of diagnostic accuracy. In this paper, we present a systematic investigation and analysis of three state of the art VLMs for histopathology, namely Quilt-Net, Quilt-LLAVA, and CONCH, on an in-house digestive pathology dataset comprising 3,507 WSIs, each in giga-pixel form, across distinct tissue types. Through a structured ablative study on cancer invasiveness and dysplasia status, we develop a comprehensive prompt engineering framework that systematically varies domain specificity, anatomical precision, instructional framing, and output constraints. Our findings demonstrate that prompt engineering significantly impacts model performance, with the CONCH model achieving the highest accuracy when provided with precise anatomical references. Additionally, we identify the critical importance of anatomical context in histopathological image analysis, as performance consistently degraded when reducing anatomical precision. We also show that model complexity alone does not guarantee superior performance, as effective domain alignment and domain-specific training are critical. These results establish foundational guidelines for prompt engineering in computational pathology and highlight the potential of VLMs to enhance diagnostic accuracy when properly instructed with domain-appropriate prompts.
Authors: Michal Geyer, Omer Tov, Linyi Jin, Richard Tucker, Inbar Mosseri, Tali Dekel, Noah Snavely
Abstract: The rising popularity of immersive visual experiences has increased interest in stereoscopic 3D video generation. Despite significant advances in video synthesis, creating 3D videos remains challenging due to the relative scarcity of 3D video data. We propose a simple approach for transforming a text-to-video generator into a video-to-stereo generator. Given an input video, our framework automatically produces the video frames from a shifted viewpoint, enabling a compelling 3D effect. Prior and concurrent approaches for this task typically operate in multiple phases, first estimating video disparity or depth, then warping the video accordingly to produce a second view, and finally inpainting the disoccluded regions. This approach inherently fails when the scene involves specular surfaces or transparent objects. In such cases, single-layer disparity estimation is insufficient, resulting in artifacts and incorrect pixel shifts during warping. Our work bypasses these restrictions by directly synthesizing the new viewpoint, avoiding any intermediate steps. This is achieved by leveraging a pre-trained video model's priors on geometry, object materials, optics, and semantics, without relying on external geometry models or manually disentangling geometry from the synthesis process. We demonstrate the advantages of our approach in complex, real-world scenarios featuring diverse object materials and compositions. See videos on https://video-eye2eye.github.io
Authors: Minh-Hao Van, Xintao Wu
Abstract: The rapid evolution of social media has provided enhanced communication channels for individuals to create online content, enabling them to express their thoughts and opinions. Multimodal memes, often utilized for playful or humorous expressions with visual and textual elements, are sometimes misused to disseminate hate speech against individuals or groups. While the detection of hateful memes is well-researched, developing effective methods to transform hateful content in memes remains a significant challenge. Leveraging the powerful generation and reasoning capabilities of Vision-Language Models (VLMs), we address the tasks of detecting and mitigating hateful content. This paper presents two key contributions: first, a definition-guided prompting technique for detecting hateful memes, and second, a unified framework for mitigating hateful content in memes, named UnHateMeme, which works by replacing hateful textual and/or visual components. With our definition-guided prompts, VLMs achieve impressive performance on hateful memes detection task. Furthermore, our UnHateMeme framework, integrated with VLMs, demonstrates a strong capability to convert hateful memes into non-hateful forms that meet human-level criteria for hate speech and maintain multimodal coherence between image and text. Through empirical experiments, we show the effectiveness of state-of-the-art pretrained VLMs such as LLaVA, Gemini and GPT-4o on the proposed tasks, providing a comprehensive analysis of their respective strengths and limitations for these tasks. This paper aims to shed light on important applications of VLMs for ensuring safe and respectful online environments.
Authors: Jannik L\"ubberstedt, Esteban Rivera, Nico Uhlemann, Markus Lienkamp
Abstract: Large Vision Language Models (LVLMs) have shown strong capabilities in understanding and analyzing visual scenes across various domains. However, in the context of autonomous driving, their limited comprehension of 3D environments restricts their effectiveness in achieving a complete and safe understanding of dynamic surroundings. To address this, we introduce V3LMA, a novel approach that enhances 3D scene understanding by integrating Large Language Models (LLMs) with LVLMs. V3LMA leverages textual descriptions generated from object detections and video inputs, significantly boosting performance without requiring fine-tuning. Through a dedicated preprocessing pipeline that extracts 3D object data, our method improves situational awareness and decision-making in complex traffic scenarios, achieving a score of 0.56 on the LingoQA benchmark. We further explore different fusion strategies and token combinations with the goal of advancing the interpretation of traffic scenes, ultimately enabling safer autonomous driving systems.
Authors: Kelsey Allen, Carl Doersch, Guangyao Zhou, Mohammed Suhail, Danny Driess, Ignacio Rocco, Yulia Rubanova, Thomas Kipf, Mehdi S. M. Sajjadi, Kevin Murphy, Joao Carreira, Sjoerd van Steenkiste
Abstract: A current limitation of video generative video models is that they generate plausible looking frames, but poor motion -- an issue that is not well captured by FVD and other popular methods for evaluating generated videos. Here we go beyond FVD by developing a metric which better measures plausible object interactions and motion. Our novel approach is based on auto-encoding point tracks and yields motion features that can be used to not only compare distributions of videos (as few as one generated and one ground truth, or as many as two datasets), but also for evaluating motion of single videos. We show that using point tracks instead of pixel reconstruction or action recognition features results in a metric which is markedly more sensitive to temporal distortions in synthetic data, and can predict human evaluations of temporal consistency and realism in generated videos obtained from open-source models better than a wide range of alternatives. We also show that by using a point track representation, we can spatiotemporally localize generative video inconsistencies, providing extra interpretability of generated video errors relative to prior work. An overview of the results and link to the code can be found on the project page: http://trajan-paper.github.io.
Authors: Ankit Amrutkar, Bj\"orn Kampa, Volkmar Schulz, Johannes Stegmaier, Markus Rothermel, Dorit Merhof
Abstract: Computer-generated holography (CGH) enables applications in holographic augmented reality (AR), 3D displays, systems neuroscience, and optical trapping. The fundamental challenge in CGH is solving the inverse problem of phase retrieval from intensity measurements. Physics-inspired neural networks (PINNs), especially Gerchberg-Saxton-based PINNs (GS-PINNs), have advanced phase retrieval capabilities. However, their performance strongly depends on forward models (FMs) and their hyperparameters (FMHs), limiting generalization, complicating benchmarking, and hindering hardware optimization. We present a systematic sensitivity analysis framework based on Saltelli's extension of Sobol's method to quantify FMH impacts on GS-PINN performance. Our analysis demonstrates that SLM pixel-resolution is the primary factor affecting neural network sensitivity, followed by pixel-pitch, propagation distance, and wavelength. Free space propagation forward models demonstrate superior neural network performance compared to Fourier holography, providing enhanced parameterization and generalization. We introduce a composite evaluation metric combining performance consistency, generalization capability, and hyperparameter perturbation resilience, establishing a unified benchmarking standard across CGH configurations. Our research connects physics-inspired deep learning theory with practical CGH implementations through concrete guidelines for forward model selection, neural network architecture, and performance evaluation. Our contributions advance the development of robust, interpretable, and generalizable neural networks for diverse holographic applications, supporting evidence-based decisions in CGH research and implementation.
Authors: Xiaoman Zhang, Juli\'an N. Acosta, Josh Miller, Ouwen Huang, Pranav Rajpurkar
Abstract: We present ReXGradient-160K, representing the largest publicly available chest X-ray dataset to date in terms of the number of patients. This dataset contains 160,000 chest X-ray studies with paired radiological reports from 109,487 unique patients across 3 U.S. health systems (79 medical sites). This comprehensive dataset includes multiple images per study and detailed radiology reports, making it particularly valuable for the development and evaluation of AI systems for medical imaging and automated report generation models. The dataset is divided into training (140,000 studies), validation (10,000 studies), and public test (10,000 studies) sets, with an additional private test set (10,000 studies) reserved for model evaluation on the ReXrank benchmark. By providing this extensive dataset, we aim to accelerate research in medical imaging AI and advance the state-of-the-art in automated radiological analysis. Our dataset will be open-sourced at https://huggingface.co/datasets/rajpurkarlab/ReXGradient-160K.
URLs: https://huggingface.co/datasets/rajpurkarlab/ReXGradient-160K.
Authors: Yuxuan Yan, Shiqi Jiang, Ting Cao, Yifan Yang, Qianqian Yang, Yuanchao Shu, Yuqing Yang, Lili Qiu
Abstract: AI-driven video analytics has become increasingly pivotal across diverse domains. However, existing systems are often constrained to specific, predefined tasks, limiting their adaptability in open-ended analytical scenarios. The recent emergence of Video-Language Models (VLMs) as transformative technologies offers significant potential for enabling open-ended video understanding, reasoning, and analytics. Nevertheless, their limited context windows present challenges when processing ultra-long video content, which is prevalent in real-world applications. To address this, we introduce AVA, a VLM-powered system designed for open-ended, advanced video analytics. AVA incorporates two key innovations: (1) the near real-time construction of Event Knowledge Graphs (EKGs) for efficient indexing of long or continuous video streams, and (2) an agentic retrieval-generation mechanism that leverages EKGs to handle complex and diverse queries. Comprehensive evaluations on public benchmarks, LVBench and VideoMME-Long, demonstrate that AVA achieves state-of-the-art performance, attaining 62.3% and 64.1% accuracy, respectively, significantly surpassing existing VLM and video Retrieval-Augmented Generation (RAG) systems. Furthermore, to evaluate video analytics in ultra-long and open-world video scenarios, we introduce a new benchmark, AVA-100. This benchmark comprises 8 videos, each exceeding 10 hours in duration, along with 120 manually annotated, diverse, and complex question-answer pairs. On AVA-100, AVA achieves top-tier performance with an accuracy of 75.8%.
Authors: Changjun Li, Runqing Jiang, Zhuo Song, Pengpeng Yu, Ye Zhang, Yulan Guo
Abstract: Post-training quantization (PTQ) has evolved as a prominent solution for compressing complex models, which advocates a small calibration dataset and avoids end-to-end retraining. However, most existing PTQ methods employ block-wise reconstruction, which neglects cross-block dependency and exhibits a notable accuracy drop in low-bit cases. To address these limitations, this paper presents a novel PTQ method, dubbed Pack-PTQ. First, we design a Hessian-guided adaptive packing mechanism to partition blocks into non-overlapping packs, which serve as the base unit for reconstruction, thereby preserving the cross-block dependency and enabling accurate quantization parameters estimation. Second, based on the pack configuration, we propose a mixed-precision quantization approach to assign varied bit-widths to packs according to their distinct sensitivities, thereby further enhancing performance. Extensive experiments on 2D image and 3D point cloud classification tasks, using various network architectures, demonstrate the superiority of our method over the state-of-the-art PTQ methods.
Authors: Md Asaduzzaman Jabin, Hanqi Jiang, Yiwei Li, Patrick Kaggwa, Eugene Douglass, Juliet N. Sekandi, Tianming Liu
Abstract: Chronic diseases, including diabetes, hypertension, asthma, HIV-AIDS, epilepsy, and tuberculosis, necessitate rigorous adherence to medication to avert disease progression, manage symptoms, and decrease mortality rates. Adherence is frequently undermined by factors including patient behavior, caregiver support, elevated medical costs, and insufficient healthcare infrastructure. We propose AdCare-VLM, a specialized Video-LLaVA-based multimodal large vision language model (LVLM) aimed at visual question answering (VQA) concerning medication adherence through patient videos. We employ a private dataset comprising 806 custom-annotated tuberculosis (TB) medication monitoring videos, which have been labeled by clinical experts, to fine-tune the model for adherence pattern detection. We present LLM-TB-VQA, a detailed medical adherence VQA dataset that encompasses positive, negative, and ambiguous adherence cases. Our method identifies correlations between visual features, such as the clear visibility of the patient's face, medication, water intake, and the act of ingestion, and their associated medical concepts in captions. This facilitates the integration of aligned visual-linguistic representations and improves multimodal interactions. Experimental results indicate that our method surpasses parameter-efficient fine-tuning (PEFT) enabled VLM models, such as LLaVA-V1.5 and Chat-UniVi, with absolute improvements ranging from 3.1% to 3.54% across pre-trained, regular, and low-rank adaptation (LoRA) configurations. Comprehensive ablation studies and attention map visualizations substantiate our approach, enhancing interpretability.
Authors: Xinlong Zhao, Shan Du
Abstract: Gas leaks pose significant risks to human health and the environment. Despite long-standing concerns, there are limited methods that can efficiently and accurately detect and segment leaks due to their concealed appearance and random shapes. In this paper, we propose a Fine-grained Spatial-Temporal Perception (FGSTP) algorithm for gas leak segmentation. FGSTP captures critical motion clues across frames and integrates them with refined object features in an end-to-end network. Specifically, we first construct a correlation volume to capture motion information between consecutive frames. Then, the fine-grained perception progressively refines the object-level features using previous outputs. Finally, a decoder is employed to optimize boundary segmentation. Because there is no highly precise labeled dataset for gas leak segmentation, we manually label a gas leak video dataset, GasVid. Experimental results on GasVid demonstrate that our model excels in segmenting non-rigid objects such as gas leaks, generating the most accurate mask compared to other state-of-the-art (SOTA) models.
Authors: Biling Wang, Austen Maniscalco, Ti Bai, Siqiu Wang, Michael Dohopolski, Mu-Han Lin, Chenyang Shen, Dan Nguyen, Junzhou Huang, Steve Jiang, Xinlei Wang
Abstract: Purpose: This study presents a Deep Learning (DL)-based quality assessment (QA) approach for evaluating auto-generated contours (auto-contours) in radiotherapy, with emphasis on Online Adaptive Radiotherapy (OART). Leveraging Bayesian Ordinal Classification (BOC) and calibrated uncertainty thresholds, the method enables confident QA predictions without relying on ground truth contours or extensive manual labeling. Methods: We developed a BOC model to classify auto-contour quality and quantify prediction uncertainty. A calibration step was used to optimize uncertainty thresholds that meet clinical accuracy needs. The method was validated under three data scenarios: no manual labels, limited labels, and extensive labels. For rectum contours in prostate cancer, we applied geometric surrogate labels when manual labels were absent, transfer learning when limited, and direct supervision when ample labels were available. Results: The BOC model delivered robust performance across all scenarios. Fine-tuning with just 30 manual labels and calibrating with 34 subjects yielded over 90% accuracy on test data. Using the calibrated threshold, over 93% of the auto-contours' qualities were accurately predicted in over 98% of cases, reducing unnecessary manual reviews and highlighting cases needing correction. Conclusion: The proposed QA model enhances contouring efficiency in OART by reducing manual workload and enabling fast, informed clinical decisions. Through uncertainty quantification, it ensures safer, more reliable radiotherapy workflows.
Authors: Muhammad Salman, Iqra Tariq, Mishal Zulfiqar, Muqadas Jalal, Sami Aujla, Sumbal Fatima
Abstract: Deepfake detection has become increasingly important due to the rise of synthetic media, which poses significant risks to digital identity and cyber presence for security and trust. While multiple approaches have improved detection accuracy, challenges remain in achieving consistent performance across diverse datasets and manipulation types. In response, we propose a novel two-tier ensemble framework for deepfake detection based on deep learning that hierarchically combines multiple instances of three state-of-the-art architectures: Xception, Res2Net101, and EfficientNet-B7. Our framework employs a unique approach where each architecture is instantiated three times with different initializations to enhance model diversity, followed by a learnable weighting mechanism that dynamically combines their predictions. Unlike traditional fixed-weight ensembles, our first-tier averages predictions within each architecture family to reduce model variance, while the second tier learns optimal contribution weights through backpropagation, automatically adjusting each architecture's influence based on their detection reliability. Our experiments achieved state-of-the-art intra-dataset performance with AUC scores of 99.22% (FF++) and 100.00% (CelebDF-v2), and F1 scores of 98.06% (FF++) and 99.94% (CelebDF-v2) without augmentation. With augmentation, we achieve AUC scores of 99.47% (FF++) and 100.00% (CelebDF-v2), and F1 scores of 98.43% (FF++) and 99.95% (CelebDF-v2). The framework demonstrates robust cross-dataset generalization, achieving AUC scores of 88.20% and 72.52%, and F1 scores of 93.16% and 80.62% in cross-dataset evaluations.
Authors: Luigi Sigillo, Christian Bianchi, Danilo Comminiello
Abstract: Image Super-Resolution is a fundamental problem in computer vision with broad applications spacing from medical imaging to satellite analysis. The ability to reconstruct high-resolution images from low-resolution inputs is crucial for enhancing downstream tasks such as object detection and segmentation. While deep learning has significantly advanced SR, achieving high-quality reconstructions with fine-grained details and realistic textures remains challenging, particularly at high upscaling factors. Recent approaches leveraging diffusion models have demonstrated promising results, yet they often struggle to balance perceptual quality with structural fidelity. In this work, we introduce ResQu a novel SR framework that integrates a quaternion wavelet preprocessing framework with latent diffusion models, incorporating a new quaternion wavelet- and time-aware encoder. Unlike prior methods that simply apply wavelet transforms within diffusion models, our approach enhances the conditioning process by exploiting quaternion wavelet embeddings, which are dynamically integrated at different stages of denoising. Furthermore, we also leverage the generative priors of foundation models such as Stable Diffusion. Extensive experiments on domain-specific datasets demonstrate that our method achieves outstanding SR results, outperforming in many cases existing approaches in perceptual quality and standard evaluation metrics. The code will be available after the revision process.
Authors: Seungjun Shin, Suji Kim, Dokwan Oh
Abstract: Implicit neural representations (INR) has found successful applications across diverse domains. To employ INR in real-life, it is important to speed up training. In the field of INR for video applications, the state-of-the-art approach employs grid-type parametric encoding and successfully achieves a faster encoding speed in comparison to its predecessors. However, the grid usage, which does not consider the video's dynamic nature, leads to redundant use of trainable parameters. As a result, it has significantly lower parameter efficiency and higher bitrate compared to NeRV-style methods that do not use a parametric encoding. To address the problem, we propose Neural Video representation with Temporally coherent Modulation (NVTM), a novel framework that can capture dynamic characteristics of video. By decomposing the spatio-temporal 3D video data into a set of 2D grids with flow information, NVTM enables learning video representation rapidly and uses parameter efficiently. Our framework enables to process temporally corresponding pixels at once, resulting in the fastest encoding speed for a reasonable video quality, especially when compared to the NeRV-style method, with a speed increase of over 3 times. Also, it remarks an average of 1.54dB/0.019 improvements in PSNR/LPIPS on UVG (Dynamic) (even with 10% fewer parameters) and an average of 1.84dB/0.013 improvements in PSNR/LPIPS on MCL-JCV (Dynamic), compared to previous grid-type works. By expanding this to compression tasks, we demonstrate comparable performance to video compression standards (H.264, HEVC) and recent INR approaches for video compression. Additionally, we perform extensive experiments demonstrating the superior performance of our algorithm across diverse tasks, encompassing super resolution, frame interpolation and video inpainting. Project page is https://sujiikim.github.io/NVTM/.
Authors: M. A. D. Buser, D. C. Simons, M. Fitski, M. H. W. A. Wijnen, A. S. Littooij, A. H. ter Brugge, I. N. Vos, M. H. A. Janse, M. de Boer, R. ter Maat, J. Sato, S. Kido, S. Kondo, S. Kasai, M. Wodzinski, H. Muller, J. Ye, J. He, Y. Kirchhoff, M. R. Rokkus, G. Haokai, S. Zitong, M. Fern\'andez-Pat\'on, D. Veiga-Canuto, D. G. Ellis, M. R. Aizenberg, B. H. M. van der Velden, H. Kuijf, A. De Luca, A. F. W. van der Steeg
Abstract: Surgery plays an important role within the treatment for neuroblastoma, a common pediatric cancer. This requires careful planning, often via magnetic resonance imaging (MRI)-based anatomical 3D models. However, creating these models is often time-consuming and user dependent. We organized the Surgical Planning in Pediatric Neuroblastoma (SPPIN) challenge, to stimulate developments on this topic, and set a benchmark for fully automatic segmentation of neuroblastoma on multi-model MRI. The challenge started with a training phase, where teams received 78 sets of MRI scans from 34 patients, consisting of both diagnostic and post-chemotherapy MRI scans. The final test phase, consisting of 18 MRI sets from 9 patients, determined the ranking of the teams. Ranking was based on the Dice similarity coefficient (Dice score), the 95th percentile of the Hausdorff distance (HD95) and the volumetric similarity (VS). The SPPIN challenge was hosted at MICCAI 2023. The final leaderboard consisted of 9 teams. The highest-ranking team achieved a median Dice score 0.82, a median HD95 of 7.69 mm and a VS of 0.91, utilizing a large, pretrained network called STU-Net. A significant difference for the segmentation results between diagnostic and post-chemotherapy MRI scans was observed (Dice = 0.89 vs Dice = 0.59, P = 0.01) for the highest-ranking team. SPPIN is the first medical segmentation challenge in extracranial pediatric oncology. The highest-ranking team used a large pre-trained network, suggesting that pretraining can be of use in small, heterogenous datasets. Although the results of the highest-ranking team were high for most patients, segmentation especially in small, pre-treated tumors were insufficient. Therefore, more reliable segmentation methods are needed to create clinically applicable models to aid surgical planning in pediatric neuroblastoma.
Authors: Feng Xue, Wenzhuang Xu, Guofeng Zhong, Anlong Minga, Nicu Sebe
Abstract: Open-vocabulary 3D panoptic segmentation has recently emerged as a significant trend. Top-performing methods currently integrate 2D segmentation with geometry-aware 3D primitives. However, the advantage would be lost without high-fidelity 3D point clouds, such as methods based on Neural Radiance Field (NeRF). These methods are limited by the insufficient capacity to maintain consistency across partial observations. To address this, recent works have utilized contrastive loss or cross-view association pre-processing for view consensus. In contrast to them, we present Cues3D, a compact approach that relies solely on NeRF instead of pre-associations. The core idea is that NeRF's implicit 3D field inherently establishes a globally consistent geometry, enabling effective object distinction without explicit cross-view supervision. We propose a three-phase training framework for NeRF, initialization-disambiguation-refinement, whereby the instance IDs are corrected using the initially-learned knowledge. Additionally, an instance disambiguation method is proposed to match NeRF-rendered 3D masks and ensure globally unique 3D instance identities. With the aid of Cues3D, we obtain highly consistent and unique 3D instance ID for each object across views with a balanced version of NeRF. Our experiments are conducted on ScanNet v2, ScanNet200, ScanNet++, and Replica datasets for 3D instance, panoptic, and semantic segmentation tasks. Cues3D outperforms other 2D image-based methods and competes with the latest 2D-3D merging based methods, while even surpassing them when using additional 3D point clouds. The code link could be found in the appendix and will be released on \href{https://github.com/mRobotit/Cues3D}{github}
Authors: Anjith George, Sebastien Marcel
Abstract: Cross-spectral face recognition systems are designed to enhance the performance of facial recognition systems by enabling cross-modal matching under challenging operational conditions. A particularly relevant application is the matching of near-infrared (NIR) images to visible-spectrum (VIS) images, enabling the verification of individuals by comparing NIR facial captures acquired with VIS reference images. The use of NIR imaging offers several advantages, including greater robustness to illumination variations, better visibility through glasses and glare, and greater resistance to presentation attacks. Despite these claimed benefits, the robustness of NIR-based systems against presentation attacks has not been systematically studied in the literature. In this work, we conduct a comprehensive evaluation into the vulnerability of NIR-VIS cross-spectral face recognition systems to presentation attacks. Our empirical findings indicate that, although these systems exhibit a certain degree of reliability, they remain vulnerable to specific attacks, emphasizing the need for further research in this area.
Authors: Wenxuan Liu, Yao Deng, Kang Chen, Xian Zhong, Zhaofei Yu, Tiejun Huang
Abstract: Existing saliency detection methods struggle in real-world scenarios due to motion blur and occlusions. In contrast, spike cameras, with their high temporal resolution, significantly enhance visual saliency maps. However, the composite noise inherent to spike camera imaging introduces discontinuities in saliency detection. Low-quality samples further distort model predictions, leading to saliency bias. To address these challenges, we propose Spike-navigated Optimal TrAnsport Saliency Region Detection (SOTA), a framework that leverages the strengths of spike cameras while mitigating biases in both spatial and temporal dimensions. Our method introduces Spike-based Micro-debias (SM) to capture subtle frame-to-frame variations and preserve critical details, even under minimal scene or lighting changes. Additionally, Spike-based Global-debias (SG) refines predictions by reducing inconsistencies across diverse conditions. Extensive experiments on real and synthetic datasets demonstrate that SOTA outperforms existing methods by eliminating composite noise bias. Our code and dataset will be released at https://github.com/lwxfight/sota.
Authors: Xia Yuan, Hai Yuan, Wenyi Ge, Ying Fu, Xi Wu, Guanyu Xing
Abstract: High-quality, animatable 3D human avatar reconstruction from monocular videos offers significant potential for reducing reliance on complex hardware, making it highly practical for applications in game development, augmented reality, and social media. However, existing methods still face substantial challenges in capturing fine geometric details and maintaining animation stability, particularly under dynamic or complex poses. To address these issues, we propose a novel real-time framework for animatable human avatar reconstruction based on 2D Gaussian Splatting (2DGS). By leveraging 2DGS and global SMPL pose parameters, our framework not only aligns positional and rotational discrepancies but also enables robust and natural pose-driven animation of the reconstructed avatars. Furthermore, we introduce a Rotation Compensation Network (RCN) that learns rotation residuals by integrating local geometric features with global pose parameters. This network significantly improves the handling of non-rigid deformations and ensures smooth, artifact-free pose transitions during animation. Experimental results demonstrate that our method successfully reconstructs realistic and highly animatable human avatars from monocular videos, effectively preserving fine-grained details while ensuring stable and natural pose variation. Our approach surpasses current state-of-the-art methods in both reconstruction quality and animation robustness on public benchmarks.
Authors: Ruiyuan Zhang, Qi Wang, Jiaxiang Liu, Yu Zhang, Yuchi Huo, Chao Wu
Abstract: 3D part assembly aims to understand part relationships and predict their 6-DoF poses to construct realistic 3D shapes, addressing the growing demand for autonomous assembly, which is crucial for robots. Existing methods mainly estimate the transformation of each part by training neural networks under supervision, which requires a substantial quantity of manually labeled data. However, the high cost of data collection and the immense variability of real-world shapes and parts make traditional methods impractical for large-scale applications. In this paper, we propose first a zero-shot part assembly method that utilizes pre-trained point cloud diffusion models as discriminators in the assembly process, guiding the manipulation of parts to form realistic shapes. Specifically, we theoretically demonstrate that utilizing a diffusion model for zero-shot part assembly can be transformed into an Iterative Closest Point (ICP) process. Then, we propose a novel pushing-away strategy to address the overlap parts, thereby further enhancing the robustness of the method. To verify our work, we conduct extensive experiments and quantitative comparisons to several strong baseline methods, demonstrating the effectiveness of the proposed approach, which even surpasses the supervised learning method. The code has been released on https://github.com/Ruiyuan-Zhang/Zero-Shot-Assembly.
Authors: Gregory Schroeder, Mohamed Sabry, Cristina Olaverri-Monreal
Abstract: The problem of calibration from straight lines is fundamental in geometric computer vision, with well-established theoretical foundations. However, its practical applicability remains limited, particularly in real-world outdoor scenarios. These environments pose significant challenges due to diverse and cluttered scenes, interrupted reprojections of straight 3D lines, and varying lighting conditions, making the task notoriously difficult. Furthermore, the field lacks a dedicated dataset encouraging the development of respective detection algorithms. In this study, we present a small dataset named "ClearLines", and by detailing its creation process, provide practical insights that can serve as a guide for developing and refining straight 3D line detection algorithms.
Authors: Kwon Byung-Ki, Qi Dai, Lee Hyoseok, Chong Luo, Tae-Hyun Oh
Abstract: We present JointDiT, a diffusion transformer that models the joint distribution of RGB and depth. By leveraging the architectural benefit and outstanding image prior of the state-of-the-art diffusion transformer, JointDiT not only generates high-fidelity images but also produces geometrically plausible and accurate depth maps. This solid joint distribution modeling is achieved through two simple yet effective techniques that we propose, i.e., adaptive scheduling weights, which depend on the noise levels of each modality, and the unbalanced timestep sampling strategy. With these techniques, we train our model across all noise levels for each modality, enabling JointDiT to naturally handle various combinatorial generation tasks, including joint generation, depth estimation, and depth-conditioned image generation by simply controlling the timestep of each branch. JointDiT demonstrates outstanding joint generation performance. Furthermore, it achieves comparable results in depth estimation and depth-conditioned image generation, suggesting that joint distribution modeling can serve as a replaceable alternative to conditional generation. The project page is available at https://byungki-k.github.io/JointDiT/.
Authors: Antoni Bigata, Rodrigo Mira, Stella Bounareli, Micha{\l} Stypu{\l}kowski, Konstantinos Vougioukas, Stavros Petridis, Maja Pantic
Abstract: Lip synchronization, known as the task of aligning lip movements in an existing video with new input audio, is typically framed as a simpler variant of audio-driven facial animation. However, as well as suffering from the usual issues in talking head generation (e.g., temporal consistency), lip synchronization presents significant new challenges such as expression leakage from the input video and facial occlusions, which can severely impact real-world applications like automated dubbing, but are often neglected in existing works. To address these shortcomings, we present KeySync, a two-stage framework that succeeds in solving the issue of temporal consistency, while also incorporating solutions for leakage and occlusions using a carefully designed masking strategy. We show that KeySync achieves state-of-the-art results in lip reconstruction and cross-synchronization, improving visual quality and reducing expression leakage according to LipLeak, our novel leakage metric. Furthermore, we demonstrate the effectiveness of our new masking approach in handling occlusions and validate our architectural choices through several ablation studies. Code and model weights can be found at https://antonibigata.github.io/KeySync.
Authors: Suho Ryu, Kihyun Kim, Eugene Baek, Dongsoo Shin, Joonseok Lee
Abstract: A variety of text-guided image editing models have been proposed recently. However, there is no widely-accepted standard evaluation method mainly due to the subjective nature of the task, letting researchers rely on manual user study. To address this, we introduce a novel Human-Aligned benchmark for Text-guided Image Editing (HATIE). Providing a large-scale benchmark set covering a wide range of editing tasks, it allows reliable evaluation, not limited to specific easy-to-evaluate cases. Also, HATIE provides a fully-automated and omnidirectional evaluation pipeline. Particularly, we combine multiple scores measuring various aspects of editing so as to align with human perception. We empirically verify that the evaluation of HATIE is indeed human-aligned in various aspects, and provide benchmark results on several state-of-the-art models to provide deeper insights on their performance.
Authors: Esteban Rivera, Surya Prabhakaran, Markus Lienkamp
Abstract: Active Learning has proved to be a relevant approach to perform sample selection for training models for Autonomous Driving. Particularly, previous works on active learning for 3D object detection have shown that selection of samples in uncontrolled scenarios is challenging. Furthermore, current approaches focus exclusively on the theoretical aspects of the sample selection problem but neglect the practical insights that can be obtained from the extensive literature and application of 3D detection models. In this paper, we introduce HeAL (Heuristical-enhanced Active Learning for 3D Object Detection) which integrates those heuristical features together with Localization and Classification to deliver the most contributing samples to the model's training. In contrast to previous works, our approach integrates heuristical features such as object distance and point-quantity to estimate the uncertainty, which enhance the usefulness of selected samples to train detection models. Our quantitative evaluation on KITTI shows that HeAL presents competitive mAP with respect to the State-of-the-Art, and achieves the same mAP as the full-supervised baseline with only 24% of the samples.
Authors: Esteban Rivera, Loic Stratil, Markus Lienkamp
Abstract: Deep learning models for object detection in autonomous driving have recently achieved impressive performance gains and are already being deployed in vehicles worldwide. However, current models require increasingly large datasets for training. Acquiring and labeling such data is costly, necessitating the development of new strategies to optimize this process. Active learning is a promising approach that has been extensively researched in the image domain. In our work, we extend this concept to the LiDAR domain by developing several inconsistency-based sample selection strategies and evaluate their effectiveness in various settings. Our results show that using a naive inconsistency approach based on the number of detected boxes, we achieve the same mAP as the random sampling strategy with 50% of the labeled data.
Authors: Nguyen Hoang Khoi Tran, Julie Stephany Berrio, Mao Shan, Zhenxing Ming, Stewart Worrall
Abstract: Intersections are geometric and functional key points in every road network. They offer strong landmarks to correct GNSS dropouts and anchor new sensor data in up-to-date maps. Despite that importance, intersection detectors either ignore the rich semantic information already computed onboard or depend on scarce, hand-labeled intersection datasets. To close that gap, this paper presents a LiDAR-based method for intersection detection that (i) fuses semantic road segmentation with vehicle localization to detect intersection candidates in a bird's eye view (BEV) representation and (ii) refines those candidates by analyzing branch topology with a least squares formulation. To evaluate our method, we introduce an automated benchmarking pipeline that pairs detections with OpenStreetMap (OSM) intersection nodes using precise GNSS/INS ground-truth poses. Tested on eight SemanticKITTI sequences, the approach achieves a mean localization error of 1.9 m, 89% precision, and 77% recall at a 5 m tolerance, outperforming the latest learning-based baseline. Moreover, the method is robust to segmentation errors higher than those of the benchmark model, demonstrating its applicability in the real world.
Authors: Muhammad Imran Zaman, Usama Ijaz Bajwa, Gulshan Saleem, Rana Hammad Raza
Abstract: Vision sensors are becoming more important in Intelligent Transportation Systems (ITS) for traffic monitoring, management, and optimization as the number of network cameras continues to rise. However, manual object tracking and matching across multiple non-overlapping cameras pose significant challenges in city-scale urban traffic scenarios. These challenges include handling diverse vehicle attributes, occlusions, illumination variations, shadows, and varying video resolutions. To address these issues, we propose an efficient and cost-effective deep learning-based framework for Multi-Object Multi-Camera Tracking (MO-MCT). The proposed framework utilizes Mask R-CNN for object detection and employs Non-Maximum Suppression (NMS) to select target objects from overlapping detections. Transfer learning is employed for re-identification, enabling the association and generation of vehicle tracklets across multiple cameras. Moreover, we leverage appropriate loss functions and distance measures to handle occlusion, illumination, and shadow challenges. The final solution identification module performs feature extraction using ResNet-152 coupled with Deep SORT based vehicle tracking. The proposed framework is evaluated on the 5th AI City Challenge dataset (Track 3), comprising 46 camera feeds. Among these 46 camera streams, 40 are used for model training and validation, while the remaining six are utilized for model testing. The proposed framework achieves competitive performance with an IDF1 score of 0.8289, and precision and recall scores of 0.9026 and 0.8527 respectively, demonstrating its effectiveness in robust and accurate vehicle tracking.
Authors: Jorgen Cani, Christos Diou, Spyridon Evangelatos, Panagiotis Radoglou-Grammatikis, Vasileios Argyriou, Panagiotis Sarigiannidis, Iraklis Varlamis, Georgios Th. Papadopoulos
Abstract: In the field of X-ray security applications, even the smallest details can significantly impact outcomes. Objects that are heavily occluded or intentionally concealed pose a great challenge for detection, whether by human observation or through advanced technological applications. While certain Deep Learning (DL) architectures demonstrate strong performance in processing local information, such as Convolutional Neural Networks (CNNs), others excel in handling distant information, e.g., transformers. In X-ray security imaging the literature has been dominated by the use of CNN-based methods, while the integration of the two aforementioned leading architectures has not been sufficiently explored. In this paper, various hybrid CNN-transformer architectures are evaluated against a common CNN object detection baseline, namely YOLOv8. In particular, a CNN (HGNetV2) and a hybrid CNN-transformer (Next-ViT-S) backbone are combined with different CNN/transformer detection heads (YOLOv8 and RT-DETR). The resulting architectures are comparatively evaluated on three challenging public X-ray inspection datasets, namely EDS, HiXray, and PIDray. Interestingly, while the YOLOv8 detector with its default backbone (CSP-DarkNet53) is generally shown to be advantageous on the HiXray and PIDray datasets, when a domain distribution shift is incorporated in the X-ray images (as happens in the EDS datasets), hybrid CNN-transformer architectures exhibit increased robustness. Detailed comparative evaluation results, including object-level detection performance and object-size error analysis, demonstrate the strengths and weaknesses of each architectural combination and suggest guidelines for future research. The source code and network weights of the models employed in this study are available at https://github.com/jgenc/xray-comparative-evaluation.
Authors: Lucas Robinet, Ahmad Berjaoui, Elizabeth Cohen-Jonathan Moyal
Abstract: Multimodal magnetic resonance imaging (MRI) constitutes the first line of investigation for clinicians in the care of brain tumors, providing crucial insights for surgery planning, treatment monitoring, and biomarker identification. Pre-training on large datasets have been shown to help models learn transferable representations and adapt with minimal labeled data. This behavior is especially valuable in medical imaging, where annotations are often scarce. However, applying this paradigm to multimodal medical data introduces a challenge: most existing approaches assume that all imaging modalities are available during both pre-training and fine-tuning. In practice, missing modalities often occur due to acquisition issues, specialist unavailability, or specific experimental designs on small in-house datasets. Consequently, a common approach involves training a separate model for each desired modality combination, making the process both resource-intensive and impractical for clinical use. Therefore, we introduce BM-MAE, a masked image modeling pre-training strategy tailored for multimodal MRI data. The same pre-trained model seamlessly adapts to any combination of available modalities, extracting rich representations that capture both intra- and inter-modal information. This allows fine-tuning on any subset of modalities without requiring architectural changes, while still benefiting from a model pre-trained on the full set of modalities. Extensive experiments show that the proposed pre-training strategy outperforms or remains competitive with baselines that require separate pre-training for each modality subset, while substantially surpassing training from scratch on several downstream tasks. Additionally, it can quickly and efficiently reconstruct missing modalities, highlighting its practical value. Code and trained models are available at: https://github.com/Lucas-rbnt/bmmae
Authors: Enmin Zhong, Carlos R. del-Blanco, Daniel Berj\'on, Fernando Jaureguizar, Narciso Garc\'ia
Abstract: Recently, there has been a surge of interest in applying deep learning techniques to animal behavior recognition, particularly leveraging pre-trained visual language models, such as CLIP, due to their remarkable generalization capacity across various downstream tasks. However, adapting these models to the specific domain of animal behavior recognition presents two significant challenges: integrating motion information and devising an effective temporal modeling scheme. In this paper, we propose AnimalMotionCLIP to address these challenges by interleaving video frames and optical flow information in the CLIP framework. Additionally, several temporal modeling schemes using an aggregation of classifiers are proposed and compared: dense, semi dense, and sparse. As a result, fine temporal actions can be correctly recognized, which is of vital importance in animal behavior analysis. Experiments on the Animal Kingdom dataset demonstrate that AnimalMotionCLIP achieves superior performance compared to state-of-the-art approaches.
Authors: Mathis Morales, Golnaz Habibi
Abstract: Detecting and tracking objects is a crucial component of any autonomous navigation method. For the past decades, object detection has yielded promising results using neural networks on various datasets. While many methods focus on performance metrics, few projects focus on improving the robustness of these detection and tracking pipelines, notably to sensor failures. In this paper we attempt to address this issue by creating a realistic synthetic data augmentation pipeline for camera-radar Autonomous Vehicle (AV) datasets. Our goal is to accurately simulate sensor failures and data deterioration due to real-world interferences. We also present our results of a baseline lightweight Noise Recognition neural network trained and tested on our augmented dataset, reaching an overall recognition accuracy of 54.4\% on 11 categories across 10086 images and 2145 radar point-clouds.
Authors: Shuo Tong, Shangde Gao, Ke Liu, Zihang Huang, Hongxia Xu, Haochao Ying, Jian Wu
Abstract: Automatic disease image grading is a significant application of artificial intelligence for healthcare, enabling faster and more accurate patient assessments. However, domain shifts, which are exacerbated by data imbalance, introduce bias into the model, posing deployment difficulties in clinical applications. To address the problem, we propose a novel \textbf{U}ncertainty-aware \textbf{M}ulti-experts \textbf{K}nowledge \textbf{D}istillation (UMKD) framework to transfer knowledge from multiple expert models to a single student model. Specifically, to extract discriminative features, UMKD decouples task-agnostic and task-specific features with shallow and compact feature alignment in the feature space. At the output space, an uncertainty-aware decoupled distillation (UDD) mechanism dynamically adjusts knowledge transfer weights based on expert model uncertainties, ensuring robust and reliable distillation. Additionally, UMKD also tackles the problems of model architecture heterogeneity and distribution discrepancies between source and target domains, which are inadequately tackled by previous KD approaches. Extensive experiments on histology prostate grading (\textit{SICAPv2}) and fundus image grading (\textit{APTOS}) demonstrate that UMKD achieves a new state-of-the-art in both source-imbalanced and target-imbalanced scenarios, offering a robust and practical solution for real-world disease image grading.
Authors: Alexander Puzicha, Konstantin W\"ustefeld, Kathrin Wilms, Frank Weichert
Abstract: The future of inland navigation increasingly relies on autonomous systems and remote operations, emphasizing the need for accurate vessel trajectory prediction. This study addresses the challenges of video-based vessel tracking and prediction by integrating advanced object detection methods, Kalman filters, and spline-based interpolation. However, existing detection systems often misclassify objects in inland waterways due to complex surroundings. A comparative evaluation of tracking algorithms, including BoT-SORT, Deep OC-SORT, and ByeTrack, highlights the robustness of the Kalman filter in providing smoothed trajectories. Experimental results from diverse scenarios demonstrate improved accuracy in predicting vessel movements, which is essential for collision avoidance and situational awareness. The findings underline the necessity of customized datasets and models for inland navigation. Future work will expand the datasets and incorporate vessel classification to refine predictions, supporting both autonomous systems and human operators in complex environments.
Authors: Wallace Lee, YuHao Chen
Abstract: Monitoring dietary habits is crucial for preventing health risks associated with overeating and undereating, including obesity, diabetes, and cardiovascular diseases. Traditional methods for tracking food intake rely on self-reported data before or after the eating, which are prone to inaccuracies. This study proposes an approach to accurately monitor ingest behaviours by leveraging 3D food models constructed from monocular 2D video. Using COLMAP and pose estimation algorithms, we generate detailed 3D representations of food, allowing us to observe changes in food volume as it is consumed. Experiments with toy models and real food items demonstrate the approach's potential. Meanwhile, we have proposed a new methodology for automated state recognition challenges to accurately detect state changes and maintain model fidelity. The 3D reconstruction approach shows promise in capturing comprehensive dietary behaviour insights, ultimately contributing to the development of automated and accurate dietary monitoring tools.
Authors: Simon Giebenhain, Tobias Kirschstein, Martin R\"unz, Lourdes Agapito, Matthias Nie{\ss}ner
Abstract: We address the 3D reconstruction of human faces from a single RGB image. To this end, we propose Pixel3DMM, a set of highly-generalized vision transformers which predict per-pixel geometric cues in order to constrain the optimization of a 3D morphable face model (3DMM). We exploit the latent features of the DINO foundation model, and introduce a tailored surface normal and uv-coordinate prediction head. We train our model by registering three high-quality 3D face datasets against the FLAME mesh topology, which results in a total of over 1,000 identities and 976K images. For 3D face reconstruction, we propose a FLAME fitting opitmization that solves for the 3DMM parameters from the uv-coordinate and normal estimates. To evaluate our method, we introduce a new benchmark for single-image face reconstruction, which features high diversity facial expressions, viewing angles, and ethnicities. Crucially, our benchmark is the first to evaluate both posed and neutral facial geometry. Ultimately, our method outperforms the most competitive baselines by over 15% in terms of geometric accuracy for posed facial expressions.
Authors: Neng Dong, Shuanglin Yan, Liyan Zhang, Jinhui Tang
Abstract: Visible-Infrared Person Re-Identification (VI-ReID) is a challenging task due to the large modality discrepancy between visible and infrared images, which complicates the alignment of their features into a suitable common space. Moreover, style noise, such as illumination and color contrast, reduces the identity discriminability and modality invariance of features. To address these challenges, we propose a novel Diverse Semantics-guided Feature Alignment and Decoupling (DSFAD) network to align identity-relevant features from different modalities into a textual embedding space and disentangle identity-irrelevant features within each modality. Specifically, we develop a Diverse Semantics-guided Feature Alignment (DSFA) module, which generates pedestrian descriptions with diverse sentence structures to guide the cross-modality alignment of visual features. Furthermore, to filter out style information, we propose a Semantic Margin-guided Feature Decoupling (SMFD) module, which decomposes visual features into pedestrian-related and style-related components, and then constrains the similarity between the former and the textual embeddings to be at least a margin higher than that between the latter and the textual embeddings. Additionally, to prevent the loss of pedestrian semantics during feature decoupling, we design a Semantic Consistency-guided Feature Restitution (SCFR) module, which further excavates useful information for identification from the style-related features and restores it back into the pedestrian-related features, and then constrains the similarity between the features after restitution and the textual embeddings to be consistent with that between the features before decoupling and the textual embeddings. Extensive experiments on three VI-ReID datasets demonstrate the superiority of our DSFAD.
Authors: Zhongying Deng, Haoyu Wang, Ziyan Huang, Lipei Zhang, Angelica I. Aviles-Rivero, Chaoyu Liu, Junjun He, Zoe Kourtzi, Carola-Bibiane Sch\"onlieb
Abstract: Brain diseases, such as Alzheimer's disease and brain tumors, present profound challenges due to their complexity and societal impact. Recent advancements in brain foundation models have shown significant promise in addressing a range of brain-related tasks. However, current brain foundation models are limited by task and data homogeneity, restricted generalization beyond segmentation or classification, and inefficient adaptation to diverse clinical tasks. In this work, we propose SAM-Brain3D, a brain-specific foundation model trained on over 66,000 brain image-label pairs across 14 MRI sub-modalities, and Hypergraph Dynamic Adapter (HyDA), a lightweight adapter for efficient and effective downstream adaptation. SAM-Brain3D captures detailed brain-specific anatomical and modality priors for segmenting diverse brain targets and broader downstream tasks. HyDA leverages hypergraphs to fuse complementary multi-modal data and dynamically generate patient-specific convolutional kernels for multi-scale feature fusion and personalized patient-wise adaptation. Together, our framework excels across a broad spectrum of brain disease segmentation and classification tasks. Extensive experiments demonstrate that our method consistently outperforms existing state-of-the-art approaches, offering a new paradigm for brain disease analysis through multi-modal, multi-scale, and dynamic foundation modeling.
Authors: Muyi Bao, Shuchang Lyu, Zhaoyang Xu, Huiyu Zhou, Jinchang Ren, Shiming Xiang, Xiangtai Li, Guangliang Cheng
Abstract: Deep learning has profoundly transformed remote sensing, yet prevailing architectures like Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) remain constrained by critical trade-offs: CNNs suffer from limited receptive fields, while ViTs grapple with quadratic computational complexity, hindering their scalability for high-resolution remote sensing data. State Space Models (SSMs), particularly the recently proposed Mamba architecture, have emerged as a paradigm-shifting solution, combining linear computational scaling with global context modeling. This survey presents a comprehensive review of Mamba-based methodologies in remote sensing, systematically analyzing about 120 studies to construct a holistic taxonomy of innovations and applications. Our contributions are structured across five dimensions: (i) foundational principles of vision Mamba architectures, (ii) micro-architectural advancements such as adaptive scan strategies and hybrid SSM formulations, (iii) macro-architectural integrations, including CNN-Transformer-Mamba hybrids and frequency-domain adaptations, (iv) rigorous benchmarking against state-of-the-art methods in multiple application tasks, such as object detection, semantic segmentation, change detection, etc. and (v) critical analysis of unresolved challenges with actionable future directions. By bridging the gap between SSM theory and remote sensing practice, this survey establishes Mamba as a transformative framework for remote sensing analysis. To our knowledge, this paper is the first systematic review of Mamba architectures in remote sensing. Our work provides a structured foundation for advancing research in remote sensing systems through SSM-based methods. We curate an open-source repository (https://github.com/BaoBao0926/Awesome-Mamba-in-Remote-Sensing) to foster community-driven advancements.
URLs: https://github.com/BaoBao0926/Awesome-Mamba-in-Remote-Sensing)
Authors: Kirtan Rajesh, Suvidha Rupesh Kumar
Abstract: Urban air pollution remains a pressing global concern, particularly in densely populated and traffic-intensive metropolitan areas like Delhi, where exposure to harmful pollutants severely impacts public health. Delhi, being one of the most polluted cities globally, experiences chronic air quality issues due to vehicular emissions, industrial activities, and construction dust, which exacerbate its already fragile atmospheric conditions. Traditional pollution mitigation strategies, such as static air purifying installations, often fail to maximize their impact due to suboptimal placement and limited adaptability to dynamic urban environments. This study presents a novel deep reinforcement learning (DRL) framework to optimize the placement of air purification booths to improve the air quality index (AQI) in the city of Delhi. We employ Proximal Policy Optimization (PPO), a state-of-the-art reinforcement learning algorithm, to iteratively learn and identify high-impact locations based on multiple spatial and environmental factors, including population density, traffic patterns, industrial influence, and green space constraints. Our approach is benchmarked against conventional placement strategies, including random and greedy AQI-based methods, using multi-dimensional performance evaluation metrics such as AQI improvement, spatial coverage, population and traffic impact, and spatial entropy. Experimental results demonstrate that the RL-based approach outperforms baseline methods by achieving a balanced and effective distribution of air purification infrastructure. Notably, the DRL framework achieves an optimal trade-off between AQI reduction and high-coverage deployment, ensuring equitable environmental benefits across urban regions. The findings underscore the potential of AI-driven spatial optimization in advancing smart city initiatives and data-driven urban air quality management.
Authors: Tiange Luo, Lajanugen Logeswaran, Justin Johnson, Honglak Lee
Abstract: We introduce RegionFocus, a visual test-time scaling approach for Vision Language Model Agents. Understanding webpages is challenging due to the visual complexity of GUI images and the large number of interface elements, making accurate action selection difficult. Our approach dynamically zooms in on relevant regions, reducing background clutter and improving grounding accuracy. To support this process, we propose an image-as-map mechanism that visualizes key landmarks at each step, providing a transparent action record and enables the agent to effectively choose among action candidates. Even with a simple region selection strategy, we observe significant performance gains of 28+\% on Screenspot-pro and 24+\% on WebVoyager benchmarks on top of two state-of-the-art open vision language model agents, UI-TARS and Qwen2.5-VL, highlighting the effectiveness of visual test-time scaling in interactive settings. We achieve a new state-of-the-art grounding performance of 61.6\% on the ScreenSpot-Pro benchmark by applying RegionFocus to a Qwen2.5-VL-72B model. Our code will be released publicly at https://github.com/tiangeluo/RegionFocus.
Authors: Wayne Wu, Honglin He, Chaoyuan Zhang, Jack He, Seth Z. Zhao, Ran Gong, Quanyi Li, Bolei Zhou
Abstract: Micromobility, which utilizes lightweight mobile machines moving in urban public spaces, such as delivery robots and mobility scooters, emerges as a promising alternative to vehicular mobility. Current micromobility depends mostly on human manual operation (in-person or remote control), which raises safety and efficiency concerns when navigating busy urban environments full of unpredictable obstacles and pedestrians. Assisting humans with AI agents in maneuvering micromobility devices presents a viable solution for enhancing safety and efficiency. In this work, we present a scalable urban simulation solution to advance autonomous micromobility. First, we build URBAN-SIM - a high-performance robot learning platform for large-scale training of embodied agents in interactive urban scenes. URBAN-SIM contains three critical modules: Hierarchical Urban Generation pipeline, Interactive Dynamics Generation strategy, and Asynchronous Scene Sampling scheme, to improve the diversity, realism, and efficiency of robot learning in simulation. Then, we propose URBAN-BENCH - a suite of essential tasks and benchmarks to gauge various capabilities of the AI agents in achieving autonomous micromobility. URBAN-BENCH includes eight tasks based on three core skills of the agents: Urban Locomotion, Urban Navigation, and Urban Traverse. We evaluate four robots with heterogeneous embodiments, such as the wheeled and legged robots, across these tasks. Experiments on diverse terrains and urban structures reveal each robot's strengths and limitations.
Authors: Hanwen Jiang, Hao Tan, Peng Wang, Haian Jin, Yue Zhao, Sai Bi, Kai Zhang, Fujun Luan, Kalyan Sunkavalli, Qixing Huang, Georgios Pavlakos
Abstract: We present RayZer, a self-supervised multi-view 3D Vision model trained without any 3D supervision, i.e., camera poses and scene geometry, while exhibiting emerging 3D awareness. Concretely, RayZer takes unposed and uncalibrated images as input, recovers camera parameters, reconstructs a scene representation, and synthesizes novel views. During training, RayZer relies solely on its self-predicted camera poses to render target views, eliminating the need for any ground-truth camera annotations and allowing RayZer to be trained with 2D image supervision. The emerging 3D awareness of RayZer is attributed to two key factors. First, we design a self-supervised framework, which achieves 3D-aware auto-encoding of input images by disentangling camera and scene representations. Second, we design a transformer-based model in which the only 3D prior is the ray structure, connecting camera, pixel, and scene simultaneously. RayZer demonstrates comparable or even superior novel view synthesis performance than ``oracle'' methods that rely on pose annotations in both training and testing. Project: https://hwjiang1510.github.io/RayZer/
Authors: Dongzhi Jiang, Ziyu Guo, Renrui Zhang, Zhuofan Zong, Hao Li, Le Zhuo, Shilin Yan, Pheng-Ann Heng, Hongsheng Li
Abstract: Recent advancements in large language models have demonstrated how chain-of-thought (CoT) and reinforcement learning (RL) can improve performance. However, applying such reasoning strategies to the visual generation domain remains largely unexplored. In this paper, we present T2I-R1, a novel reasoning-enhanced text-to-image generation model, powered by RL with a bi-level CoT reasoning process. Specifically, we identify two levels of CoT that can be utilized to enhance different stages of generation: (1) the semantic-level CoT for high-level planning of the prompt and (2) the token-level CoT for low-level pixel processing during patch-by-patch generation. To better coordinate these two levels of CoT, we introduce BiCoT-GRPO with an ensemble of generation rewards, which seamlessly optimizes both generation CoTs within the same training step. By applying our reasoning strategies to the baseline model, Janus-Pro, we achieve superior performance with 13% improvement on T2I-CompBench and 19% improvement on the WISE benchmark, even surpassing the state-of-the-art model FLUX.1. Code is available at: https://github.com/CaraJ7/T2I-R1
Authors: Anthony D Martin
Abstract: We propose a generalization of modern representation learning objectives by reframing them as recursive divergence alignment processes over localized conditional distributions While recent frameworks like Information Contrastive Learning I-Con unify multiple learning paradigms through KL divergence between fixed neighborhood conditionals we argue this view underplays a crucial recursive structure inherent in the learning process. We introduce Recursive KL Divergence Optimization RKDO a dynamic formalism where representation learning is framed as the evolution of KL divergences across data neighborhoods. This formulation captures contrastive clustering and dimensionality reduction methods as static slices while offering a new path to model stability and local adaptation. Our experiments demonstrate that RKDO offers dual efficiency advantages approximately 30 percent lower loss values compared to static approaches across three different datasets and 60 to 80 percent reduction in computational resources needed to achieve comparable results. This suggests that RKDOs recursive updating mechanism provides a fundamentally more efficient optimization landscape for representation learning with significant implications for resource constrained applications.
Authors: Taiga Hayami, Kakeru Koizumi, Hiroshi Watanabe
Abstract: Implicit Neural Representations (INRs) have garnered significant attention for their ability to model complex signals across a variety of domains. Recently, INR-based approaches have emerged as promising frameworks for neural video compression. While conventional methods primarily focus on embedding video content into compact neural networks for efficient representation, they often struggle to reconstruct high-frequency details under stringent model size constraints, which are critical in practical compression scenarios. To address this limitation, we propose an INR-based video representation method that integrates a general-purpose super-resolution (SR) network. Motivated by the observation that high-frequency components exhibit low temporal redundancy across frames, our method entrusts the reconstruction of fine details to the SR network. Experimental results demonstrate that the proposed method outperforms conventional INR-based baselines in terms of reconstruction quality, while maintaining comparable model sizes.
Authors: Siqi Li, Yufan Shen, Xiangnan Chen, Jiayi Chen, Hengwei Ju, Haodong Duan, Song Mao, Hongbin Zhou, Bo Zhang, Pinlong Cai, Licheng Wen, Botian Shi, Yong Liu, Xinyu Cai, Yu Qiao
Abstract: The rapid advancement of multimodal large language models (MLLMs) has profoundly impacted the document domain, creating a wide array of application scenarios. This progress highlights the need for a comprehensive benchmark to evaluate these models' capabilities across various document-specific tasks. However, existing benchmarks often fail to locate specific model weaknesses or guide systematic improvements. To bridge this gap, we introduce a General Document Intelligence Benchmark (GDI-Bench), featuring 1.9k images across 9 key scenarios and 19 document-specific tasks. By decoupling visual complexity and reasoning complexity, the GDI-Bench structures graded tasks that allow performance assessment by difficulty, aiding in model weakness identification and optimization guidance. We evaluate the GDI-Bench on various open-source and closed-source models, conducting decoupled analyses in the visual and reasoning domains. For instance, the GPT-4o model excels in reasoning tasks but exhibits limitations in visual capabilities. To address the diverse tasks and domains in the GDI-Bench, we propose a GDI Model that mitigates the issue of catastrophic forgetting during the supervised fine-tuning (SFT) process through a intelligence-preserving training strategy. Our model achieves state-of-the-art performance on previous benchmarks and the GDI-Bench. Both our benchmark and model will be open source.
Authors: Sandrine B\'edard, Jan Valo\v{s}ek, Valeria Oliva, Kenneth A. Weber II, Julien Cohen-Adad
Abstract: Spinal cord functional MRI studies require precise localization of spinal levels for reliable voxelwise group analyses. Traditional template-based registration of the spinal cord uses intervertebral discs for alignment. However, substantial anatomical variability across individuals exists between vertebral and spinal levels. This study proposes a novel registration approach that leverages spinal nerve rootlets to improve alignment accuracy and reproducibility across individuals. We developed a registration method leveraging dorsal cervical rootlets segmentation and aligning them non-linearly with the PAM50 spinal cord template. Validation was performed on a multi-subject, multi-site dataset (n=267, 44 sites) and a multi-subject dataset with various neck positions (n=10, 3 sessions). We further validated the method on task-based functional MRI (n=23) to compare group-level activation maps using rootlet-based registration to traditional disc-based methods. Rootlet-based registration showed superior alignment across individuals compared to the traditional disc-based method. Notably, rootlet positions were more stable across neck positions. Group-level analysis of task-based functional MRI using rootlet-based increased Z scores and activation cluster size compared to disc-based registration (number of active voxels from 3292 to 7978). Rootlet-based registration enhances both inter- and intra-subject anatomical alignment and yields better spatial normalization for group-level fMRI analyses. Our findings highlight the potential of rootlet-based registration to improve the precision and reliability of spinal cord neuroimaging group analysis.
Authors: Hwihun Jeong, Hayeon Lee, Se Young Chun, Jongho Lee
Abstract: Blind harmonization has emerged as a promising technique for MR image harmonization to achieve scale-invariant representations, requiring only target domain data (i.e., no source domain data necessary). However, existing methods face limitations such as inter-slice heterogeneity in 3D, moderate image quality, and limited performance for a large domain gap. To address these challenges, we introduce BlindHarmonyDiff, a novel blind 3D harmonization framework that leverages an edge-to-image model tailored specifically to harmonization. Our framework employs a 3D rectified flow trained on target domain images to reconstruct the original image from an edge map, then yielding a harmonized image from the edge of a source domain image. We propose multi-stride patch training for efficient 3D training and a refinement module for robust inference by suppressing hallucination. Extensive experiments demonstrate that BlindHarmonyDiff outperforms prior arts by harmonizing diverse source domain images to the target domain, achieving higher correspondence to the target domain characteristics. Downstream task-based quality assessments such as tissue segmentation and age prediction on diverse MR scanners further confirm the effectiveness of our approach and demonstrate the capability of our robust and generalizable blind harmonization.
Authors: Rafael C. Pinto, Anderson R. Tavares
Abstract: Proto-objects - image regions that share common visual properties - offer a promising alternative to traditional attention mechanisms based on rectangular-shaped image patches in neural networks. Although previous work demonstrated that evolving a patch-based hard-attention module alongside a controller network could achieve state-of-the-art performance in visual reinforcement learning tasks, our approach leverages image segmentation to work with higher-level features. By operating on proto-objects rather than fixed patches, we significantly reduce the representational complexity: each image decomposes into fewer proto-objects than regular patches, and each proto-object can be efficiently encoded as a compact feature vector. This enables a substantially smaller self-attention module that processes richer semantic information. Our experiments demonstrate that this proto-object-based approach matches or exceeds the state-of-the-art performance of patch-based implementations with 62% less parameters and 2.6 times less training time.
Authors: Xuyang Guo, Jiayan Huo, Zhenmei Shi, Zhao Song, Jiahao Zhang, Jiale Zhao
Abstract: Text-to-video generative models have made significant strides in recent years, producing high-quality videos that excel in both aesthetic appeal and accurate instruction following, and have become central to digital art creation and user engagement online. Yet, despite these advancements, their ability to respect fundamental physical laws remains largely untested: many outputs still violate basic constraints such as rigid-body collisions, energy conservation, and gravitational dynamics, resulting in unrealistic or even misleading content. Existing physical-evaluation benchmarks typically rely on automatic, pixel-level metrics applied to simplistic, life-scenario prompts, and thus overlook both human judgment and first-principles physics. To fill this gap, we introduce \textbf{T2VPhysBench}, a first-principled benchmark that systematically evaluates whether state-of-the-art text-to-video systems, both open-source and commercial, obey twelve core physical laws including Newtonian mechanics, conservation principles, and phenomenological effects. Our benchmark employs a rigorous human evaluation protocol and includes three targeted studies: (1) an overall compliance assessment showing that all models score below 0.60 on average in each law category; (2) a prompt-hint ablation revealing that even detailed, law-specific hints fail to remedy physics violations; and (3) a counterfactual robustness test demonstrating that models often generate videos that explicitly break physical rules when so instructed. The results expose persistent limitations in current architectures and offer concrete insights for guiding future research toward truly physics-aware video generation.
Authors: Usman Muhammad, Jorma Laaksonen, Lyudmila Mihaylova
Abstract: Deep neural networks have demonstrated highly competitive performance in super-resolution (SR) for natural images by learning mappings from low-resolution (LR) to high-resolution (HR) images. However, hyperspectral super-resolution remains an ill-posed problem due to the high spectral dimensionality of the data and the scarcity of available training samples. Moreover, existing methods often rely on large models with a high number of parameters or require the fusion with panchromatic or RGB images, both of which are often impractical in real-world scenarios. Inspired by the MobileNet architecture, we introduce a lightweight depthwise separable dilated convolutional network (DSDCN) to address the aforementioned challenges. Specifically, our model leverages multiple depthwise separable convolutions, similar to the MobileNet architecture, and further incorporates a dilated convolution fusion block to make the model more flexible for the extraction of both spatial and spectral features. In addition, we propose a custom loss function that combines mean squared error (MSE), an L2 norm regularization-based constraint, and a spectral angle-based loss, ensuring the preservation of both spectral and spatial details. The proposed model achieves very competitive performance on two publicly available hyperspectral datasets, making it well-suited for hyperspectral image super-resolution tasks. The source codes are publicly available at: \href{https://github.com/Usman1021/lightweight}{https://github.com/Usman1021/lightweight}.
URLs: https://github.com/Usman1021/lightweight, https://github.com/Usman1021/lightweight
Authors: Julian Christopher L. Maya, Johnenn R. Manalang, Maricor N. Soriano
Abstract: CorStitch is an open-source software developed to automate the creation of accurate georeferenced reef mosaics from video transects obtained through Automated Rapid Reef Assessment System surveys. We utilized a Fourier-based image correlation algorithm to stitch sequential video frames, aligning them with synchronized GNSS timestamps. The resulting compressed Keyhole Markup Language files, compatible with geographic information systems such as Google Earth, enable detailed spatial analysis. Validation through comparative analysis of mosaics from two temporally distinct surveys of the same reef demonstrated the software's consistent and reliable performance.
Authors: Abu Saleh Musa Miah, taro Suzuki, Jungpil Shin
Abstract: Parkinsons Disease (PD) is a progressive neurological disorder that primarily affects motor functions and can lead to mild cognitive impairment (MCI) and dementia in its advanced stages. With approximately 10 million people diagnosed globally 1 to 1.8 per 1,000 individuals, according to reports by the Japan Times and the Parkinson Foundation early and accurate diagnosis of PD is crucial for improving patient outcomes. While numerous studies have utilized machine learning (ML) and deep learning (DL) techniques for PD recognition, existing surveys are limited in scope, often focusing on single data modalities and failing to capture the potential of multimodal approaches. To address these gaps, this study presents a comprehensive review of PD recognition systems across diverse data modalities, including Magnetic Resonance Imaging (MRI), gait-based pose analysis, gait sensory data, handwriting analysis, speech test data, Electroencephalography (EEG), and multimodal fusion techniques. Based on over 347 articles from leading scientific databases, this review examines key aspects such as data collection methods, settings, feature representations, and system performance, with a focus on recognition accuracy and robustness. This survey aims to serve as a comprehensive resource for researchers, providing actionable guidance for the development of next generation PD recognition systems. By leveraging diverse data modalities and cutting-edge machine learning paradigms, this work contributes to advancing the state of PD diagnostics and improving patient care through innovative, multimodal approaches.
Authors: Merve G\"ulle, Sebastian Weing\"artner, Mehmet Ak\c{c}akaya
Abstract: Real-time (RT) dynamic MRI plays a vital role in capturing rapid physiological processes, offering unique insights into organ motion and function. Among these applications, RT cine MRI is particularly important for functional assessment of the heart with high temporal resolution. RT imaging enables free-breathing, ungated imaging of cardiac motion, making it a crucial alternative for patients who cannot tolerate conventional breath-hold, ECG-gated acquisitions. However, achieving high acceleration rates in RT cine MRI is challenging due to aliasing artifacts from extra-cardiac tissues, particularly at high undersampling factors. In this study, we propose a novel outer volume removal (OVR) method to address this challenge by eliminating aliasing contributions from non-cardiac regions in a post-processing framework. Our approach estimates the outer volume signal for each timeframe using composite temporal images from time-interleaved undersampling patterns, which inherently contain pseudo-periodic ghosting artifacts. A deep learning (DL) model is trained to identify and remove these artifacts, producing a clean outer volume estimate that is subsequently subtracted from the corresponding k-space data. The final reconstruction is performed with a physics-driven DL (PD-DL) method trained using an OVR-specific loss function to restore high spatio-temporal resolution images. Experimental results show that the proposed method at high accelerations achieves image quality that is visually comparable to clinical baseline images, while outperforming conventional reconstruction techniques, both qualitatively and quantitatively. The proposed approach provides a practical and effective solution for artifact reduction in RT cine MRI without requiring acquisition modifications, offering a pathway to higher acceleration rates while preserving diagnostic quality.
Authors: Arsha Nagrani, Sachit Menon, Ahmet Iscen, Shyamal Buch, Ramin Mehran, Nilpa Jha, Anja Hauth, Yukun Zhu, Carl Vondrick, Mikhail Sirotenko, Cordelia Schmid, Tobias Weyand
Abstract: Multimodal LLMs are turning their focus to video benchmarks, however most video benchmarks only provide outcome supervision, with no intermediate or interpretable reasoning steps. This makes it challenging to assess if models are truly able to combine perceptual and temporal information to reason about videos, or simply get the correct answer by chance or by exploiting linguistic biases. To remedy this, we provide a new video reasoning dataset called MINERVA for modern multimodal models. Each question in the dataset comes with 5 answer choices, as well as detailed, hand-crafted reasoning traces. Our dataset is multimodal, diverse in terms of video domain and length, and consists of complex multi-step questions. Extensive benchmarking shows that our dataset provides a challenge for frontier open-source and proprietary models. We perform fine-grained error analysis to identify common failure modes across various models, and create a taxonomy of reasoning errors. We use this to explore both human and LLM-as-a-judge methods for scoring video reasoning traces, and find that failure modes are primarily related to temporal localization, followed by visual perception errors, as opposed to logical or completeness errors. The dataset, along with questions, answer candidates and reasoning traces will be publicly available under https://github.com/google-deepmind/neptune?tab=readme-ov-file\#minerva.
URLs: https://github.com/google-deepmind/neptune?tab=readme-ov-file\
Authors: Aditya Arora, Zhengzhong Tu, Yufei Wang, Ruizheng Bai, Jian Wang, Sizhuo Ma
Abstract: In this paper, we propose GuideSR, a novel single-step diffusion-based image super-resolution (SR) model specifically designed to enhance image fidelity. Existing diffusion-based SR approaches typically adapt pre-trained generative models to image restoration tasks by adding extra conditioning on a VAE-downsampled representation of the degraded input, which often compromises structural fidelity. GuideSR addresses this limitation by introducing a dual-branch architecture comprising: (1) a Guidance Branch that preserves high-fidelity structures from the original-resolution degraded input, and (2) a Diffusion Branch, which a pre-trained latent diffusion model to enhance perceptual quality. Unlike conventional conditioning mechanisms, our Guidance Branch features a tailored structure for image restoration tasks, combining Full Resolution Blocks (FRBs) with channel attention and an Image Guidance Network (IGN) with guided attention. By embedding detailed structural information directly into the restoration pipeline, GuideSR produces sharper and more visually consistent results. Extensive experiments on benchmark datasets demonstrate that GuideSR achieves state-of-the-art performance while maintaining the low computational cost of single-step approaches, with up to 1.39dB PSNR gain on challenging real-world datasets. Our approach consistently outperforms existing methods across various reference-based metrics including PSNR, SSIM, LPIPS, DISTS and FID, further representing a practical advancement for real-world image restoration.
Authors: Yanbang Li, Ziyang Gong, Haoyang Li, Haoyang Li, Xiaoqi Huang, Haolan Kang, Guangping Bai, Xianzheng Ma
Abstract: Recently, natural language has been the primary medium for human-robot interaction. However, its inherent lack of spatial precision for robotic control introduces challenges such as ambiguity and verbosity. To address these limitations, we introduce the Robotic Visual Instruction (RoVI), a novel paradigm to guide robotic tasks through an object-centric, hand-drawn symbolic representation. RoVI effectively encodes spatial-temporal information into human-interpretable visual instructions through 2D sketches, utilizing arrows, circles, colors, and numbers to direct 3D robotic manipulation. To enable robots to understand RoVI better and generate precise actions based on RoVI, we present Visual Instruction Embodied Workflow (VIEW), a pipeline formulated for RoVI-conditioned policies. This approach leverages Vision-Language Models (VLMs) to interpret RoVI inputs, decode spatial and temporal constraints from 2D pixel space via keypoint extraction, and then transform them into executable 3D action sequences. We additionally curate a specialized dataset of 15K instances to fine-tune small VLMs for edge deployment, enabling them to effectively learn RoVI capabilities. Our approach is rigorously validated across 11 novel tasks in both real and simulated environments, demonstrating significant generalization capability. Notably, VIEW achieves an 87.5% success rate in real-world scenarios involving unseen tasks that feature multi-step actions, with disturbances, and trajectory-following requirements. Code and Datasets in this paper will be released soon.
Authors: Chih-Hao Lin, Zian Wang, Ruofan Liang, Yuxuan Zhang, Sanja Fidler, Shenlong Wang, Zan Gojcic
Abstract: Generating realistic and controllable weather effects in videos is valuable for many applications. Physics-based weather simulation requires precise reconstructions that are hard to scale to in-the-wild videos, while current video editing often lacks realism and control. In this work, we introduce WeatherWeaver, a video diffusion model that synthesizes diverse weather effects -- including rain, snow, fog, and clouds -- directly into any input video without the need for 3D modeling. Our model provides precise control over weather effect intensity and supports blending various weather types, ensuring both realism and adaptability. To overcome the scarcity of paired training data, we propose a novel data strategy combining synthetic videos, generative image editing, and auto-labeled real-world videos. Extensive evaluations show that our method outperforms state-of-the-art methods in weather simulation and removal, providing high-quality, physically plausible, and scene-identity-preserving results over various real-world videos.
Authors: Zeqing Xia, Bojun Xiong, Zhouhui Lian
Abstract: Font design is of vital importance in the digital content design and modern printing industry. Developing algorithms capable of automatically synthesizing vector fonts can significantly facilitate the font design process. However, existing methods mainly concentrate on raster image generation, and only a few approaches can directly synthesize vector fonts. This paper proposes an end-to-end trainable method, VecFontSDF, to reconstruct and synthesize high-quality vector fonts using signed distance functions (SDFs). Specifically, based on the proposed SDF-based implicit shape representation, VecFontSDF learns to model each glyph as shape primitives enclosed by several parabolic curves, which can be precisely converted to quadratic B\'ezier curves that are widely used in vector font products. In this manner, most image generation methods can be easily extended to synthesize vector fonts. Qualitative and quantitative experiments conducted on a publicly-available dataset demonstrate that our method obtains high-quality results on several tasks, including vector font reconstruction, interpolation, and few-shot vector font synthesis, markedly outperforming the state of the art. Our code and trained models are available at https://xiazeqing.github.io/VecFontSDF.
Authors: Yao Qiang, Chengyin Li, Prashant Khanduri, Dongxiao Zhu
Abstract: Vision Transformers (ViTs) have become prominent models for solving various vision tasks. However, the interpretability of ViTs has not kept pace with their promising performance. While there has been a surge of interest in developing {\it post hoc} solutions to explain ViTs' outputs, these methods do not generalize to different downstream tasks and various transformer architectures. Furthermore, if ViTs are not properly trained with the given data and do not prioritize the region of interest, the {\it post hoc} methods would be less effective. Instead of developing another {\it post hoc} approach, we introduce a novel training procedure that inherently enhances model interpretability. Our interpretability-aware ViT (IA-ViT) draws inspiration from a fresh insight: both the class patch and image patches consistently generate predicted distributions and attention maps. IA-ViT is composed of a feature extractor, a predictor, and an interpreter, which are trained jointly with an interpretability-aware training objective. Consequently, the interpreter simulates the behavior of the predictor and provides a faithful explanation through its single-head self-attention mechanism. Our comprehensive experimental results demonstrate the effectiveness of IA-ViT in several image classification tasks, with both qualitative and quantitative evaluations of model performance and interpretability. Source code is available from: https://github.com/qiangyao1988/IA-ViT.
Authors: Mingrui Zhu, Dongxin Chen, Xin Wei, Nannan Wang, Xinbo Gao
Abstract: In an era where personal photos are easily leaked and collected, face de-identification is a crucial method for protecting identity privacy. However, current face de-identification techniques face challenges in preserving attribute details and often produce anonymized results with reduced authenticity. These shortcomings are particularly evident when handling occlusions,frequently resulting in noticeable editing artifacts. Our primary finding in this work is that simultaneous training of identity disentanglement and anonymization hinders their respective effectiveness.Therefore, we propose "Disentangle Before Anonymize",a novel two-stage Framework(DBAF)designed for attributepreserved and occlusion-robust de-identification. This framework includes a Contrastive Identity Disentanglement (CID) module and a Key-authorized Reversible Identity Anonymization (KRIA) module, achieving faithful attribute preservation and high-quality identity anonymization edits. Additionally, we introduce a Multiscale Attentional Attribute Retention (MAAR) module to address the issue of reduced anonymization quality under occlusions.Extensive experiments demonstrate that our method outperforms state-of-the-art de-identification approaches, delivering superior quality, enhanced detail fidelity, improved attribute preservation performance, and greater robustness to occlusions.
Authors: Siamul Karim Khan, Patrick Tinsley, Mahsa Mitcheff, Patrick Flynn, Kevin W. Bowyer, Adam Czajka
Abstract: Synthesis of same-identity biometric iris images, both for existing and non-existing identities while preserving the identity across a wide range of pupil sizes, is complex due to the intricate iris muscle constriction mechanism, requiring a precise model of iris non-linear texture deformations to be embedded into the synthesis pipeline. This paper presents the first method of fully data-driven, identity-preserving, pupil size-varying synthesis of iris images. This approach is capable of synthesizing images of irises with different pupil sizes representing non-existing identities, as well as non-linearly deforming the texture of iris images of existing subjects given the segmentation mask of the target iris image. Iris recognition experiments suggest that the proposed deformation model both preserves the identity when changing the pupil size, and offers better similarity between same-identity iris samples with significant differences in pupil size, compared to state-of-the-art linear and non-linear (bio-mechanical-based) iris deformation models. Two immediate applications of the proposed approach are: (a) synthesis of, or enhancement of the existing biometric datasets for iris recognition, mimicking those acquired with iris sensors, and (b) helping forensic human experts examine iris image pairs with significant differences in pupil dilation. Images considered in this work conform to selected ISO/IEC 29794-6 quality metrics to make them applicable in biometric systems. The source codes and model weights are offered with this paper.
Authors: Jinghao Zhou, Tomas Jakab, Philip Torr, Christian Rupprecht
Abstract: Recently, 3D generative models have made impressive progress, enabling the generation of almost arbitrary 3D assets from text or image inputs. However, these approaches generate objects in isolation without any consideration for the scene where they will eventually be placed. In this paper, we propose a framework that allows for the stylization of an existing 3D asset to fit into a given 2D scene, and additionally produce a photorealistic composition as if the asset was placed within the environment. This not only opens up a new level of control for object stylization, for example, the same assets can be stylized to reflect changes in the environment, such as summer to winter or fantasy versus futuristic settings-but also makes the object-scene composition more controllable. We achieve this by combining modeling and optimizing the object's texture and environmental lighting through differentiable ray tracing with image priors from pre-trained text-to-image diffusion models. We demonstrate that our method is applicable to a wide variety of indoor and outdoor scenes and arbitrary objects. Project page: https://jensenzhoujh.github.io/scene-cond-3d/.
Authors: Xin Ma, Yaohui Wang, Xinyuan Chen, Gengyun Jia, Ziwei Liu, Yuan-Fang Li, Cunjian Chen, Yu Qiao
Abstract: We propose Latte, a novel Latent Diffusion Transformer for video generation. Latte first extracts spatio-temporal tokens from input videos and then adopts a series of Transformer blocks to model video distribution in the latent space. In order to model a substantial number of tokens extracted from videos, four efficient variants are introduced from the perspective of decomposing the spatial and temporal dimensions of input videos. To improve the quality of generated videos, we determine the best practices of Latte through rigorous experimental analysis, including video clip patch embedding, model variants, timestep-class information injection, temporal positional embedding, and learning strategies. Our comprehensive evaluation demonstrates that Latte achieves state-of-the-art performance across four standard video generation datasets, i.e., FaceForensics, SkyTimelapse, UCF101, and Taichi-HD. In addition, we extend Latte to the text-to-video generation (T2V) task, where Latte achieves results that are competitive with recent T2V models. We strongly believe that Latte provides valuable insights for future research on incorporating Transformers into diffusion models for video generation.
Authors: Zhinan Yu, Zheng Qin, Yijie Tang, Yongjun Wang, Renjiao Yi, Chenyang Zhu, Kai Xu
Abstract: This work studies the problem of unsupervised RGB-D point cloud registration, which aims at training a robust registration model without ground-truth pose supervision. Existing methods usually leverages unposed RGB-D sequences and adopt a frame-to-frame framework based on differentiable rendering to train the registration model, which enforces the photometric and geometric consistency between the two frames for supervision. However, this frame-to-frame framework is vulnerable to inconsistent factors between different frames, e.g., lighting changes, geometry occlusion, and reflective materials, which leads to suboptimal convergence of the registration model. In this paper, we propose a novel frame-to-model optimization framework named F2M-Reg for unsupervised RGB-D point cloud registration. We leverage the neural implicit field as a global model of the scene and optimize the estimated poses of the frames by registering them to the global model, and the registration model is subsequently trained with the optimized poses. Thanks to the global encoding capability of neural implicit field, our frame-to-model framework is significantly more robust to inconsistent factors between different frames and thus can provide better supervision for the registration model. Besides, we demonstrate that F2M-Reg can be further enhanced by a simplistic synthetic warming-up strategy. To this end, we construct a photorealistic synthetic dataset named Sim-RGBD to initialize the registration model for the frame-to-model optimization on real-world RGB-D sequences. Extensive experiments on four challenging benchmarks have shown that our method surpasses the previous state-of-the-art counterparts by a large margin, especially under scenarios with severe lighting changes and low overlap. Our code and models are available at https://github.com/MrIsland/F2M_Reg.
Authors: Minh Tran, Adrian De Luis, Haitao Liao, Ying Huang, Roy McCann, Alan Mantooth, Jack Cothren, Ngan Le
Abstract: As the impact of climate change escalates, the global necessity to transition to sustainable energy sources becomes increasingly evident. Renewable energies have emerged as a viable solution for users, with Photovoltaic energy being a favored choice for small installations due to its reliability and efficiency. Accurate mapping of PV installations is crucial for understanding the extension of its adoption and informing energy policy. To meet this need, we introduce S3Former, designed to segment solar panels from aerial imagery and provide size and location information critical for analyzing the impact of such installations on the grid. Solar panel identification is challenging due to factors such as varying weather conditions, roof characteristics, Ground Sampling Distance variations and lack of appropriate initialization weights for optimized training. To tackle these complexities, S3Former features a Masked Attention Mask Transformer incorporating a self-supervised learning pretrained backbone. Specifically, our model leverages low-level and high-level features extracted from the backbone and incorporates an instance query mechanism incorporated on the Transformer architecture to enhance the localization of solar PV installations. We introduce a self-supervised learning phase (pretext task) to improve the initialization weights on the backbone of S3Former. We evaluated S3Former using diverse datasets, demonstrate improvement state-of-the-art models.
Authors: Mohamed Nagy, Naoufel Werghi, Bilal Hassan, Jorge Dias, Majid Khonji
Abstract: This paper addresses limitations in 3D tracking-by-detection methods, particularly in identifying legitimate trajectories and reducing state estimation drift in Kalman filters. Existing methods often use threshold-based filtering for detection scores, which can fail for distant and occluded objects, leading to false positives. To tackle this, we propose a novel track validity mechanism and multi-stage observational gating process, significantly reducing ghost tracks and enhancing tracking performance. Our method achieves a $29.47\%$ improvement in Multi-Object Tracking Accuracy (MOTA) on the KITTI validation dataset with the Second detector. Additionally, a refined Kalman filter term reduces localization noise, improving higher-order tracking accuracy (HOTA) by $4.8\%$. The online framework, RobMOT, outperforms state-of-the-art methods across multiple detectors, with HOTA improvements of up to $3.92\%$ on the KITTI testing dataset and $8.7\%$ on the validation dataset, while achieving low identity switch scores. RobMOT excels in challenging scenarios, tracking distant objects and prolonged occlusions, with a $1.77\%$ MOTA improvement on the Waymo Open dataset, and operates at a remarkable 3221 FPS on a single CPU, proving its efficiency for real-time multi-object tracking.
Authors: Jingwei Xu, Yikai Wang, Yiqun Zhao, Yanwei Fu, Shenghua Gao
Abstract: Unveiling an empty street from crowded observations captured by in-car cameras is crucial for autonomous driving. However, removing all temporarily static objects, such as stopped vehicles and standing pedestrians, presents a significant challenge. Unlike object-centric 3D inpainting, which relies on thorough observation in a small scene, street scene cases involve long trajectories that differ from previous 3D inpainting tasks. The camera-centric moving environment of captured videos further complicates the task due to the limited degree and time duration of object observation. To address these obstacles, we introduce StreetUnveiler to reconstruct an empty street. StreetUnveiler learns a 3D representation of the empty street from crowded observations. Our representation is based on the hard-label semantic 2D Gaussian Splatting (2DGS) for its scalability and ability to identify Gaussians to be removed. We inpaint rendered image after removing unwanted Gaussians to provide pseudo-labels and subsequently re-optimize the 2DGS. Given its temporal continuous movement, we divide the empty street scene into observed, partial-observed, and unobserved regions, which we propose to locate through a rendered alpha map. This decomposition helps us to minimize the regions that need to be inpainted. To enhance the temporal consistency of the inpainting, we introduce a novel time-reversal framework to inpaint frames in reverse order and use later frames as references for earlier frames to fully utilize the long-trajectory observations. Our experiments conducted on the street scene dataset successfully reconstructed a 3D representation of the empty street. The mesh representation of the empty street can be extracted for further applications. The project page and more visualizations can be found at: https://streetunveiler.github.io
Authors: Hao Wen, Zehuan Huang, Yaohui Wang, Xinyuan Chen, Lu Sheng
Abstract: Existing single image-to-3D creation methods typically involve a two-stage process, first generating multi-view images, and then using these images for 3D reconstruction. However, training these two stages separately leads to significant data bias in the inference phase, thus affecting the quality of reconstructed results. We introduce a unified 3D generation framework, named Ouroboros3D, which integrates diffusion-based multi-view image generation and 3D reconstruction into a recursive diffusion process. In our framework, these two modules are jointly trained through a self-conditioning mechanism, allowing them to adapt to each other's characteristics for robust inference. During the multi-view denoising process, the multi-view diffusion model uses the 3D-aware maps rendered by the reconstruction module at the previous timestep as additional conditions. The recursive diffusion framework with 3D-aware feedback unites the entire process and improves geometric consistency.Experiments show that our framework outperforms separation of these two stages and existing methods that combine them at the inference phase. Project page: https://costwen.github.io/Ouroboros3D/
Authors: Zicheng Duan, Yuxuan Ding, Chenhui Gou, Ziqin Zhou, Ethan Smith, Lingqiao Liu
Abstract: Zero-shot personalized image generation models aim to produce images that align with both a given text prompt and subject image, requiring the model to incorporate both sources of guidance. Existing methods often struggle to capture fine-grained subject details and frequently prioritize one form of guidance over the other, resulting in suboptimal subject encoding and imbalanced generation. In this study, we uncover key insights into overcoming such drawbacks, notably that 1) the choice of the subject image encoder critically influences subject identity preservation and training efficiency, and 2) the text and subject guidance should take effect at different denoising stages. Building on these insights, we introduce a new approach, EZIGen, that employs two main components: leveraging a fixed pre-trained Diffusion UNet itself as subject encoder, following a process that balances the two guidances by separating their dominance stage and revisiting certain time steps to bootstrap subject transfer quality. Through these two components, EZIGen, initially built upon SD2.1-base, achieved state-of-the-art performances on multiple personalized generation benchmarks with a unified model, while using 100 times less training data. Moreover, by further migrating our design to SDXL, EZIGen is proven to be a versatile model-agnostic solution for personalized generation. Demo Page: zichengduan.github.io/pages/EZIGen/index.html
Authors: Quan Meng, Lei Li, Matthias Nie{\ss}ner, Angela Dai
Abstract: We present LT3SD, a novel latent diffusion model for large-scale 3D scene generation. Recent advances in diffusion models have shown impressive results in 3D object generation, but are limited in spatial extent and quality when extended to 3D scenes. To generate complex and diverse 3D scene structures, we introduce a latent tree representation to effectively encode both lower-frequency geometry and higher-frequency detail in a coarse-to-fine hierarchy. We can then learn a generative diffusion process in this latent 3D scene space, modeling the latent components of a scene at each resolution level. To synthesize large-scale scenes with varying sizes, we train our diffusion model on scene patches and synthesize arbitrary-sized output 3D scenes through shared diffusion generation across multiple scene patches. Through extensive experiments, we demonstrate the efficacy and benefits of LT3SD for large-scale, high-quality unconditional 3D scene generation and for probabilistic completion for partial scene observations.
Authors: Ashmal Vayani, Dinura Dissanayake, Hasindri Watawana, Noor Ahsan, Nevasini Sasikumar, Omkar Thawakar, Henok Biadglign Ademtew, Yahya Hmaiti, Amandeep Kumar, Kartik Kuckreja, Mykola Maslych, Wafa Al Ghallabi, Mihail Mihaylov, Chao Qin, Abdelrahman M Shaker, Mike Zhang, Mahardika Krisna Ihsani, Amiel Esplana, Monil Gokani, Shachar Mirkin, Harsh Singh, Ashay Srivastava, Endre Hamerlik, Fathinah Asma Izzati, Fadillah Adamsyah Maani, Sebastian Cavada, Jenny Chim, Rohit Gupta, Sanjay Manjunath, Kamila Zhumakhanova, Feno Heriniaina Rabevohitra, Azril Amirudin, Muhammad Ridzuan, Daniya Kareem, Ketan More, Kunyang Li, Pramesh Shakya, Muhammad Saad, Amirpouya Ghasemaghaei, Amirbek Djanibekov, Dilshod Azizov, Branislava Jankovic, Naman Bhatia, Alvaro Cabrera, Johan Obando-Ceron, Olympiah Otieno, Fabian Farestam, Muztoba Rabbani, Sanoojan Baliah, Santosh Sanjeev, Abduragim Shtanchaev, Maheen Fatima, Thao Nguyen, Amrin Kareem, Toluwani Aremu, Nathan Xavier, Amit Bhatkal, Hawau Toyin, Aman Chadha, Hisham Cholakkal, Rao Muhammad Anwer, Michael Felsberg, Jorma Laaksonen, Thamar Solorio, Monojit Choudhury, Ivan Laptev, Mubarak Shah, Salman Khan, Fahad Khan
Abstract: Existing Large Multimodal Models (LMMs) generally focus on only a few regions and languages. As LMMs continue to improve, it is increasingly important to ensure they understand cultural contexts, respect local sensitivities, and support low-resource languages, all while effectively integrating corresponding visual cues. In pursuit of culturally diverse global multimodal models, our proposed All Languages Matter Benchmark (ALM-bench) represents the largest and most comprehensive effort to date for evaluating LMMs across 100 languages. ALM-bench challenges existing models by testing their ability to understand and reason about culturally diverse images paired with text in various languages, including many low-resource languages traditionally underrepresented in LMM research. The benchmark offers a robust and nuanced evaluation framework featuring various question formats, including true/false, multiple choice, and open-ended questions, which are further divided into short and long-answer categories. ALM-bench design ensures a comprehensive assessment of a model's ability to handle varied levels of difficulty in visual and linguistic reasoning. To capture the rich tapestry of global cultures, ALM-bench carefully curates content from 13 distinct cultural aspects, ranging from traditions and rituals to famous personalities and celebrations. Through this, ALM-bench not only provides a rigorous testing ground for state-of-the-art open and closed-source LMMs but also highlights the importance of cultural and linguistic inclusivity, encouraging the development of models that can serve diverse global populations effectively. Our benchmark is publicly available.
Authors: Yihong Xu, Yuan Yin, \'Eloi Zablocki, Tuan-Hung Vu, Alexandre Boulch, Matthieu Cord
Abstract: Accurately predicting how agents move in dynamic scenes is essential for safe autonomous driving. State-of-the-art motion forecasting models rely on large curated datasets with manually annotated or heavily post-processed trajectories. However, building these datasets is costly, generally manual, hard to scale, and lacks reproducibility. They also introduce domain gaps that limit generalization across environments. We introduce PPT (Pretraining with Pseudo-labeled Trajectories), a simple and scalable alternative that uses unprocessed and diverse trajectories automatically generated from off-the-shelf 3D detectors and tracking. Unlike traditional pipelines aiming for clean, single-label annotations, PPT embraces noise and diversity as useful signals for learning robust representations. With optional finetuning on a small amount of labeled data, models pretrained with PPT achieve strong performance across standard benchmarks particularly in low-data regimes, and in cross-domain, end-to-end and multi-class settings. PPT is easy to implement and improves generalization in motion forecasting. Code and data will be released upon acceptance.
Authors: Simon B. Jensen, Stefan Oehmcke, Andreas M{\o}gelmose, Meysam Madadi, Christian Igel, Sergio Escalera, Thomas B. Moeslund
Abstract: Assessment of forest biodiversity is crucial for ecosystem management and conservation. While traditional field surveys provide high-quality assessments, they are labor-intensive and spatially limited. This study investigates whether deep learning-based fusion of close-range sensing data from 2D orthophotos and 3D airborne laser scanning (ALS) point clouds can reliable assess the biodiversity potential of forests. We introduce the BioVista dataset, comprising 44 378 paired samples of orthophotos and ALS point clouds from temperate forests in Denmark, designed to explore multimodal fusion approaches. Using deep neural networks (ResNet for orthophotos and PointVector for ALS point clouds), we investigate each data modality's ability to assess forest biodiversity potential, achieving overall accuracies of 76.7% and 75.8%, respectively. We explore various 2D and 3D fusion approaches: confidence-based ensembling, feature-level concatenation, and end-to-end training, achieving overall accuracies of 80.5%, 81.4% and 80.4% respectively. Our results demonstrate that spectral information from orthophotos and structural information from ALS point clouds effectively complement each other in forest biodiversity assessment.
Authors: Junjie He, Yuxiang Tuo, Binghui Chen, Chongyang Zhong, Yifeng Geng, Liefeng Bo
Abstract: Recently, large-scale generative models have demonstrated outstanding text-to-image generation capabilities. However, generating high-fidelity personalized images with specific subjects still presents challenges, especially in cases involving multiple subjects. In this paper, we propose AnyStory, a unified approach for personalized subject generation. AnyStory not only achieves high-fidelity personalization for single subjects, but also for multiple subjects, without sacrificing subject fidelity. Specifically, AnyStory models the subject personalization problem in an "encode-then-route" manner. In the encoding step, AnyStory utilizes a universal and powerful image encoder, i.e., ReferenceNet, in conjunction with CLIP vision encoder to achieve high-fidelity encoding of subject features. In the routing step, AnyStory utilizes a decoupled instance-aware subject router to accurately perceive and predict the potential location of the corresponding subject in the latent space, and guide the injection of subject conditions. Detailed experimental results demonstrate the excellent performance of our method in retaining subject details, aligning text descriptions, and personalizing for multiple subjects. The project page is at https://aigcdesigngroup.github.io/AnyStory/ .
Authors: Junxiang Qiu, Shuo Wang, Jinda Lu, Lin Liu, Houcheng Jiang, Xingyu Zhu, Yanbin Hao
Abstract: Diffusion Transformer (DiT) is a crucial method for content generation. However, it needs a lot of time to sample. Many studies have attempted to use caching to reduce the time consumption of sampling. Existing caching methods accelerate generation by reusing DiT features from the previous time step and skipping calculations in the next, but they tend to locate and cache low-error modules without focusing on reducing caching-induced errors, resulting in a sharp decline in generated content quality when increasing caching intensity. To solve this problem, we propose the Error-Optimized Cache (EOC). This method introduces three key improvements: (1) Prior knowledge extraction: Extract and process the caching differences; (2) A judgment method for cache optimization: Determine whether certain caching steps need to be optimized; (3) Cache optimization: reduce caching errors. Experiments show that this algorithm significantly reduces the error accumulation caused by caching, especially excessive caching. On the ImageNet dataset, without substantially increasing the computational load, this method improves the FID of the generated images when the rule-based model FORA has a caching level of 75%, 50%, and 25%, and the training-based model Learning-to-cache has a caching level of 22%. Specifically, the FID values change from 30.454 to 21.690 (28.8%), from 6.857 to 5.821 (15.1%), from 3.870 to 3.692 (4.6%), and from 3.539 to 3.451 (2.5%) respectively.
Authors: Fadeel Sher Khan, Joshua Ebenezer, Hamid Sheikh, Seok-Jun Lee
Abstract: Smartphone cameras have become ubiquitous imaging tools, yet their small sensors and compact optics often limit spatial resolution and introduce distortions. Combining information from multiple low-resolution (LR) frames to produce a high-resolution (HR) image has been explored to overcome the inherent limitations of smartphone cameras. Despite the promise of multi-frame super-resolution (MFSR), current approaches are hindered by datasets that fail to capture the characteristic noise and motion patterns found in real-world handheld burst images. In this work, we address this gap by introducing a novel synthetic data engine that uses multi-exposure static images to synthesize LR-HR training pairs while preserving sensor-specific noise characteristics and image motion found during handheld burst photography. We also propose MFSR-GAN: a multi-scale RAW-to-RGB network for MFSR. Compared to prior approaches, MFSR-GAN emphasizes a "base frame" throughout its architecture to mitigate artifacts. Experimental results on both synthetic and real data demonstrates that MFSR-GAN trained with our synthetic engine yields sharper, more realistic reconstructions than existing methods for real-world MFSR.
Authors: Zhiyuan Yan, Junyan Ye, Weijia Li, Zilong Huang, Shenghai Yuan, Xiangyang He, Kaiqing Lin, Jun He, Conghui He, Li Yuan
Abstract: The recent breakthroughs in OpenAI's GPT4o model have demonstrated surprisingly good capabilities in image generation and editing, resulting in significant excitement in the community. This technical report presents the first-look evaluation benchmark (named GPT-ImgEval), quantitatively and qualitatively diagnosing GPT-4o's performance across three critical dimensions: (1) generation quality, (2) editing proficiency, and (3) world knowledge-informed semantic synthesis. Across all three tasks, GPT-4o demonstrates strong performance, significantly surpassing existing methods in both image generation control and output quality, while also showcasing exceptional knowledge reasoning capabilities. Furthermore, based on the GPT-4o's generated data, we propose a classification-model-based approach to investigate the underlying architecture of GPT-4o, where our empirical results suggest the model consists of an auto-regressive (AR) combined with a diffusion-based head for image decoding, rather than the VAR-like architectures. We also provide a complete speculation on GPT-4o's overall architecture. In addition, we conduct a series of analyses to identify and visualize GPT-4o's specific limitations and the synthetic artifacts commonly observed in its image generation. We also present a comparative study of multi-round image editing between GPT-4o and Gemini 2.0 Flash, and discuss the safety implications of GPT-4o's outputs, particularly their detectability by existing image forensic models. We hope that our work can offer valuable insight and provide a reliable benchmark to guide future research, foster reproducibility, and accelerate innovation in the field of image generation and beyond. The codes and datasets used for evaluating GPT-4o can be found at https://github.com/PicoTrex/GPT-ImgEval.
Authors: Huijie Liu, Bingcan Wang, Jie Hu, Xiaoming Wei, Guoliang Kang
Abstract: Dish images play a crucial role in the digital era, with the demand for culturally distinctive dish images continuously increasing due to the digitization of the food industry and e-commerce. In general cases, existing text-to-image generation models excel in producing high-quality images; however, they struggle to capture diverse characteristics and faithful details of specific domains, particularly Chinese dishes. To address this limitation, we propose Omni-Dish, the first text-to-image generation model specifically tailored for Chinese dishes. We develop a comprehensive dish curation pipeline, building the largest dish dataset to date. Additionally, we introduce a recaption strategy and employ a coarse-to-fine training scheme to help the model better learn fine-grained culinary nuances. During inference, we enhance the user's textual input using a pre-constructed high-quality caption library and a large language model, enabling more photorealistic and faithful image generation. Furthermore, to extend our model's capability for dish editing tasks, we propose Concept-Enhanced P2P. Based on this approach, we build a dish editing dataset and train a specialized editing model. Extensive experiments demonstrate the superiority of our methods.
Authors: Jiachen Li, Qing Xie, Renshu Gu, Jinyu Xu, Yongjian Liu, Xiaohan Yu
Abstract: Zero-shot referring image segmentation aims to locate and segment the target region based on a referring expression, with the primary challenge of aligning and matching semantics across visual and textual modalities without training. Previous works address this challenge by utilizing Vision-Language Models and mask proposal networks for region-text matching. However, this paradigm may lead to incorrect target localization due to the inherent ambiguity and diversity of free-form referring expressions. To alleviate this issue, we present LGD (Leveraging Generative Descriptions), a framework that utilizes the advanced language generation capabilities of Multi-Modal Large Language Models to enhance region-text matching performance in Vision-Language Models. Specifically, we first design two kinds of prompts, the attribute prompt and the surrounding prompt, to guide the Multi-Modal Large Language Models in generating descriptions related to the crucial attributes of the referent object and the details of surrounding objects, referred to as attribute description and surrounding description, respectively. Secondly, three visual-text matching scores are introduced to evaluate the similarity between instance-level visual features and textual features, which determines the mask most associated with the referring expression. The proposed method achieves new state-of-the-art performance on three public datasets RefCOCO, RefCOCO+ and RefCOCOg, with maximum improvements of 9.97% in oIoU and 11.29% in mIoU compared to previous methods.
Authors: Jongwon Lee, Timothy Bretl
Abstract: In this paper, we present a method for localizing a query image with respect to a precomputed 3D Gaussian Splatting (3DGS) scene representation. First, the method uses 3DGS to render a synthetic RGBD image at some initial pose estimate. Second, it establishes 2D-2D correspondences between the query image and this synthetic image. Third, it uses the depth map to lift the 2D-2D correspondences to 2D-3D correspondences and solves a perspective-n-point (PnP) problem to produce a final pose estimate. Results from evaluation across three existing datasets with 38 scenes and over 2,700 test images show that our method significantly reduces both inference time (by over two orders of magnitude, from more than 10 seconds to as fast as 0.1 seconds) and estimation error compared to baseline methods that use photometric loss minimization. Results also show that our method tolerates large errors in the initial pose estimate of up to 55{\deg} in rotation and 1.1 units in translation (normalized by scene scale), achieving final pose errors of less than 5{\deg} in rotation and 0.05 units in translation on 90% of images from the Synthetic NeRF and Mip-NeRF360 datasets and on 42% of images from the more challenging Tanks and Temples dataset.
Authors: Z. S. Baltaci, K. Oksuz, S. Kuzucu, K. Tezoren, B. K. Konar, A. Ozkan, E. Akbas, S. Kalkan
Abstract: Class-wise characteristics of training examples affect the performance of deep classifiers. A well-studied example is when the number of training examples of classes follows a long-tailed distribution, a situation that is likely to yield sub-optimal performance for under-represented classes. This class imbalance problem is conventionally addressed by approaches relying on the class-wise cardinality of training examples, such as data resampling. In this paper, we demonstrate that considering solely the cardinality of classes does not cover all issues causing class imbalance. To measure class imbalance, we propose "Class Uncertainty" as the average predictive uncertainty of the training examples, and we show that this novel measure captures the differences across classes better than cardinality. We also curate SVCI-20 as a novel dataset in which the classes have equal number of training examples but they differ in terms of their hardness; thereby causing a type of class imbalance which cannot be addressed by the approaches relying on cardinality. We incorporate our "Class Uncertainty" measure into a diverse set of ten class imbalance mitigation methods to demonstrate its effectiveness on long-tailed datasets as well as on our SVCI-20. Code and datasets will be made available.
Authors: Alireza Furutanpey, Qiyang Zhang, Philipp Raith, Tobias Pfandzelter, Shangguang Wang, Schahram Dustdar
Abstract: Nanosatellite constellations equipped with sensors capturing large geographic regions provide unprecedented opportunities for Earth observation. As constellation sizes increase, network contention poses a downlink bottleneck. Orbital Edge Computing (OEC) leverages limited onboard compute resources to reduce transfer costs by processing the raw captures at the source. However, current solutions have limited practicability due to reliance on crude filtering methods or over-prioritizing particular downstream tasks. This work presents FOOL, an OEC-native and task-agnostic feature compression method that preserves prediction performance. FOOL partitions high-resolution satellite imagery to maximize throughput. Further, it embeds context and leverages inter-tile dependencies to lower transfer costs with negligible overhead. While FOOL is a feature compressor, it can recover images with competitive scores on quality measures at lower bitrates. We extensively evaluate transfer cost reduction by including the peculiarity of intermittently available network connections in low earth orbit. Lastly, we test the feasibility of our system for standardized nanosatellite form factors. We demonstrate that FOOL permits downlinking over 100x the data volume without relying on prior information on the downstream tasks.
Authors: Aneesh Chavan, Vaibhav Agrawal, Vineeth Bhat, Sarthak Chittawar, Siddharth Srivastava, Chetan Arora, K Madhava Krishna
Abstract: Re-identification (ReID) is a critical challenge in computer vision, predominantly studied in the context of pedestrians and vehicles. However, robust object-instance ReID, which has significant implications for tasks such as autonomous exploration, long-term perception, and scene understanding, remains underexplored. In this work, we address this gap by proposing a novel dual-path object-instance re-identification transformer architecture that integrates multimodal RGB and depth information. By leveraging depth data, we demonstrate improvements in ReID across scenes that are cluttered or have varying illumination conditions. Additionally, we develop a ReID-based localization framework that enables accurate camera localization and pose identification across different viewpoints. We validate our methods using two custom-built RGB-D datasets, as well as multiple sequences from the open-source TUM RGB-D datasets. Our approach demonstrates significant improvements in both object instance ReID (mAP of 75.18) and localization accuracy (success rate of 83% on TUM-RGBD), highlighting the essential role of object ReID in advancing robotic perception. Our models, frameworks, and datasets have been made publicly available.
Authors: Alexander Popov, Alperen Degirmenci, David Wehr, Shashank Hegde, Ryan Oldja, Alexey Kamenev, Bertrand Douillard, David Nist\'er, Urs Muller, Ruchi Bhargava, Stan Birchfield, Nikolai Smolyanskiy
Abstract: We propose the use of latent space generative world models to address the covariate shift problem in autonomous driving. A world model is a neural network capable of predicting an agent's next state given past states and actions. By leveraging a world model during training, the driving policy effectively mitigates covariate shift without requiring an excessive amount of training data. During end-to-end training, our policy learns how to recover from errors by aligning with states observed in human demonstrations, so that at runtime it can recover from perturbations outside the training distribution. Additionally, we introduce a novel transformer-based perception encoder that employs multi-view cross-attention and a learned scene query. We present qualitative and quantitative results, demonstrating significant improvements upon prior state of the art in closed-loop testing in the CARLA simulator, as well as showing the ability to handle perturbations in both CARLA and NVIDIA's DRIVE Sim.
Authors: Teli Ma, Zifan Wang, Jiaming Zhou, Mengmeng Wang, Junwei Liang
Abstract: Inferring affordable (i.e., graspable) parts of arbitrary objects based on human specifications is essential for robots advancing toward open-vocabulary manipulation. Current grasp planners, however, are hindered by limited vision-language comprehension and time-consuming 3D radiance modeling, restricting real-time, open-vocabulary interactions with objects. To address these limitations, we propose GLOVER, a unified Generalizable Open-Vocabulary Affordance Reasoning framework, which fine-tunes the Large Language Models (LLMs) to predict the visual affordance of graspable object parts within RGB feature space. We compile a dataset of over 10,000 images from human-object interactions, annotated with unified visual and linguistic affordance labels, to enable multi-modal fine-tuning. GLOVER inherits world knowledge and common-sense reasoning from LLMs, facilitating more fine-grained object understanding and sophisticated tool-use reasoning. To enable effective real-world deployment, we present Affordance-Aware Grasping Estimation (AGE), a non-parametric grasp planner that aligns the gripper pose with a superquadric surface derived from affordance data. In evaluations across 30 table-top real-world scenes, GLOVER achieves success rates of 86.0% in part identification and 76.3% in grasping, with speeds approximately 29 times faster in affordance reasoning and 40 times faster in grasping pose estimation than the previous state-of-the-art. We also validate the generalization across embodiments, showing effectiveness in humanoid robots with dexterous hands.
Authors: Satwik Kundu, Swaroop Ghosh
Abstract: With the growing interest in Quantum Machine Learning (QML) and the increasing availability of quantum computers through cloud providers, addressing the potential security risks associated with QML has become an urgent priority. One key concern in the QML domain is the threat of data poisoning attacks in the current quantum cloud setting. Adversarial access to training data could severely compromise the integrity and availability of QML models. Classical data poisoning techniques require significant knowledge and training to generate poisoned data, and lack noise resilience, making them ineffective for QML models in the Noisy Intermediate Scale Quantum (NISQ) era. In this work, we first propose a simple yet effective technique to measure intra-class encoder state similarity (ESS) by analyzing the outputs of encoding circuits. Leveraging this approach, we introduce a \underline{Qu}antum \underline{I}ndiscriminate \underline{D}ata Poisoning attack, QUID. Through extensive experiments conducted in both noiseless and noisy environments (e.g., IBM\_Brisbane's noise), across various architectures and datasets, QUID achieves up to $92\%$ accuracy degradation in model performance compared to baseline models and up to $75\%$ accuracy degradation compared to random label-flipping. We also tested QUID against state-of-the-art classical defenses, with accuracy degradation still exceeding $50\%$, demonstrating its effectiveness. This work represents the first attempt to reevaluate data poisoning attacks in the context of QML.
Authors: Sizhe Xing, Aolong Sun, Chengxi Wang, Yizhi Wang, Boyu Dong, Junhui Hu, Xuyu Deng, An Yan, Yingjun Liu, Fangchen Hu, Zhongya Li, Ouhan Huang, Junhao Zhao, Yingjun Zhou, Ziwei Li, Jianyang Shi, Xi Xiao, Richard Penty, Qixiang Cheng, Nan Chi, Junwen Zhang
Abstract: The rapid advancement of generative artificial intelligence (AI) in recent years has profoundly reshaped modern lifestyles, necessitating a revolutionary architecture to support the growing demands for computational power. Cloud computing has become the driving force behind this transformation. However, it consumes significant power and faces computation security risks due to the reliance on extensive data centers and servers in the cloud. Reducing power consumption while enhancing computational scale remains persistent challenges in cloud computing. Here, we propose and experimentally demonstrate an optical cloud computing system that can be seamlessly deployed across edge-metro network. By modulating inputs and models into light, a wide range of edge nodes can directly access the optical computing center via the edge-metro network. The experimental validations show an energy efficiency of 118.6 mW/TOPs (tera operations per second), reducing energy consumption by two orders of magnitude compared to traditional electronic-based cloud computing solutions. Furthermore, it is experimentally validated that this architecture can perform various complex generative AI models through parallel computing to achieve image generation tasks.
Authors: Benjamin Hou, Tejas Sudharshan Mathai, Pritam Mukherjee, Xinya Wang, Ronald M. Summers, Zhiyong Lu
Abstract: Purpose: To automate contrast phase classification in CT using organ-specific features extracted from a widely used segmentation tool with a lightweight decision tree classifier. Materials and Methods: This retrospective study utilized three public CT datasets from separate institutions. The phase prediction model was trained on the WAW-TACE (median age: 66 [60,73]; 185 males) dataset, and externally validated on the VinDr-Multiphase (146 males; 63 females; 56 unk) and C4KC-KiTS (median age: 61 [50.68; 123 males) datasets. Contrast phase classification was performed using organ-specific features extracted by TotalSegmentator, followed by prediction using a gradient-boosted decision tree classifier. Results: On the VinDr-Multiphase dataset, the phase prediction model achieved the highest or comparable AUCs across all phases (>0.937), with superior F1-scores in the non-contrast (0.994), arterial (0.937), and delayed (0.718) phases. Statistical testing indicated significant performance differences only in the arterial and delayed phases (p<0.05). On the C4KC-KiTS dataset, the phase prediction model achieved the highest AUCs across all phases (>0.991), with superior F1-scores in arterial/venous (0.968) and delayed (0.935) phases. Statistical testing confirmed significant improvements over all baseline models in these two phases (p<0.05). Performance in the non-contrast class, however, was comparable across all models, with no statistically significant differences observed (p>0.05). Conclusion: The lightweight model demonstrated strong performance relative to all baseline models, and exhibited robust generalizability across datasets from different institutions.
Authors: Jintao Zhang, Chendong Xiang, Haofeng Huang, Jia Wei, Haocheng Xi, Jun Zhu, Jianfei Chen
Abstract: An efficient attention implementation is essential for large models due to its quadratic time complexity. Fortunately, attention commonly exhibits sparsity, i.e., many values in the attention map are near zero, allowing for the omission of corresponding computations. Many studies have utilized the sparse pattern to accelerate attention. However, most existing works focus on optimizing attention within specific models by exploiting certain sparse patterns of the attention map. A universal sparse attention that guarantees both the speedup and end-to-end performance of diverse models remains elusive. In this paper, we propose SpargeAttn, a universal sparse and quantized attention for any model. Our method uses a two-stage online filter: in the first stage, we rapidly and accurately predict the attention map, enabling the skip of some matrix multiplications in attention. In the second stage, we design an online softmax-aware filter that incurs no extra overhead and further skips some matrix multiplications. Experiments show that our method significantly accelerates diverse models, including language, image, and video generation, without sacrificing end-to-end metrics. The codes are available at https://github.com/thu-ml/SpargeAttn.
Authors: Samuel Bilson, Anna Pustogvar
Abstract: Land cover classification involves the production of land cover maps, which determine the type of land through remote sensing imagery. Over recent years, such classification is being performed by machine learning classification models, which can give highly accurate predictions on land cover per pixel using large quantities of input training data. However, such models do not currently take account of input measurement uncertainty, which is vital for traceability in metrology. In this work we propose a Bayesian classification framework using generative modelling to take account of input measurement uncertainty. We take the specific case of Bayesian quadratic discriminant analysis, and apply it to land cover datasets from Copernicus Sentinel-2 in 2020 and 2021. We benchmark the performance of the model against more popular classification models used in land cover maps such as random forests and neural networks. We find that such Bayesian models are more trustworthy, in the sense that they are more interpretable, explicitly model the input measurement uncertainty, and maintain predictive performance of class probability outputs across datasets of different years and sizes, whilst also being computationally efficient.
Authors: Mehmet Can Yavuz, Berrin Yanikoglu
Abstract: We present Variational Self-Supervised Learning (VSSL), a novel framework that combines variational inference with self-supervised learning to enable efficient, decoder-free representation learning. Unlike traditional VAEs that rely on input reconstruction via a decoder, VSSL symmetrically couples two encoders with Gaussian outputs. A momentum-updated teacher network defines a dynamic, data-dependent prior, while the student encoder produces an approximate posterior from augmented views. The reconstruction term in the ELBO is replaced with a cross-view denoising objective, preserving the analytical tractability of Gaussian KL divergence. We further introduce cosine-based formulations of KL and log-likelihood terms to enhance semantic alignment in high-dimensional latent spaces. Experiments on CIFAR-10, CIFAR-100, and ImageNet-100 show that VSSL achieves competitive or superior performance to leading self-supervised methods, including BYOL and MoCo V3. VSSL offers a scalable, probabilistically grounded approach to learning transferable representations without generative reconstruction, bridging the gap between variational modeling and modern self-supervised techniques.
Authors: Hansheng Chen, Kai Zhang, Hao Tan, Zexiang Xu, Fujun Luan, Leonidas Guibas, Gordon Wetzstein, Sai Bi
Abstract: Diffusion models approximate the denoising distribution as a Gaussian and predict its mean, whereas flow matching models reparameterize the Gaussian mean as flow velocity. However, they underperform in few-step sampling due to discretization error and tend to produce over-saturated colors under classifier-free guidance (CFG). To address these limitations, we propose a novel Gaussian mixture flow matching (GMFlow) model: instead of predicting the mean, GMFlow predicts dynamic Gaussian mixture (GM) parameters to capture a multi-modal flow velocity distribution, which can be learned with a KL divergence loss. We demonstrate that GMFlow generalizes previous diffusion and flow matching models where a single Gaussian is learned with an $L_2$ denoising loss. For inference, we derive GM-SDE/ODE solvers that leverage analytic denoising distributions and velocity fields for precise few-step sampling. Furthermore, we introduce a novel probabilistic guidance scheme that mitigates the over-saturation issues of CFG and improves image generation quality. Extensive experiments demonstrate that GMFlow consistently outperforms flow matching baselines in generation quality, achieving a Precision of 0.942 with only 6 sampling steps on ImageNet 256$\times$256.
Authors: Letian Huang, Dongwei Ye, Jialin Dan, Chengzhi Tao, Huiwen Liu, Kun Zhou, Bo Ren, Yuanqi Li, Yanwen Guo, Jie Guo
Abstract: The emergence of neural and Gaussian-based radiance field methods has led to considerable advancements in novel view synthesis and 3D object reconstruction. Nonetheless, specular reflection and refraction continue to pose significant challenges due to the instability and incorrect overfitting of radiance fields to high-frequency light variations. Currently, even 3D Gaussian Splatting (3D-GS), as a powerful and efficient tool, falls short in recovering transparent objects with nearby contents due to the existence of apparent secondary ray effects. To address this issue, we propose TransparentGS, a fast inverse rendering pipeline for transparent objects based on 3D-GS. The main contributions are three-fold. Firstly, an efficient representation of transparent objects, transparent Gaussian primitives, is designed to enable specular refraction through a deferred refraction strategy. Secondly, we leverage Gaussian light field probes (GaussProbe) to encode both ambient light and nearby contents in a unified framework. Thirdly, a depth-based iterative probes query (IterQuery) algorithm is proposed to reduce the parallax errors in our probe-based framework. Experiments demonstrate the speed and accuracy of our approach in recovering transparent objects from complex environments, as well as several applications in computer graphics and vision.
Authors: Xueqi Ma, Yilin Liu, Tianlong Gao, Qirui Huang, Hui Huang
Abstract: We introduce CLR-Wire, a novel framework for 3D curve-based wireframe generation that integrates geometry and topology into a unified Continuous Latent Representation. Unlike conventional methods that decouple vertices, edges, and faces, CLR-Wire encodes curves as Neural Parametric Curves along with their topological connectivity into a continuous and fixed-length latent space using an attention-driven variational autoencoder (VAE). This unified approach facilitates joint learning and generation of both geometry and topology. To generate wireframes, we employ a flow matching model to progressively map Gaussian noise to these latents, which are subsequently decoded into complete 3D wireframes. Our method provides fine-grained modeling of complex shapes and irregular topologies, and supports both unconditional generation and generation conditioned on point cloud or image inputs. Experimental results demonstrate that, compared with state-of-the-art generative approaches, our method achieves substantial improvements in accuracy, novelty, and diversity, offering an efficient and comprehensive solution for CAD design, geometric reconstruction, and 3D content creation.