Peer Revenue Returns subject to peer review

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computer Vision

cs.CV Watch Computer Vision

Sunday 8 February

Computer Vision · Cross-listed from cs.AI

Selective Fine-Tuning for Targeted and Robust Concept Unlearning

Mansi, Avinash Kori, Francesca Toni et al. (+1 more)

Text guided diffusion models are used by millions of users, but can be easily exploited to produce harmful content. Concept unlearning methods aim at reducing the models' likelihood of generating harmful content. Traditionally, this has been tackled at an individual concept level, with only a handful of recent works considering more realistic concept combinations. However, state of the art methods depend on full finetuning, which is computationally expensive. Concept localisation methods can facilitate selective finetuning, but existing techniques are static, resulting in suboptimal utility. In order to tackle these challenges, we propose TRUST (Targeted Robust Selective fine Tuning), a novel approach for dynamically estimating target concept neurons and unlearning them through selective finetuning, empowered by a Hessian based regularization. We show experimentally, against a number of SOTA baselines, that TRUST is robust against adversarial prompts, preserves generation quality to a significant degree, and is also significantly faster than the SOTA. Our method achieves unlearning of not only individual concepts but also combinations of concepts and conditional concepts, without any specific regularization.
Read the full abstract

All authors Mansi, Avinash Kori, Francesca Toni, Soteris Demetriou

Computer Vision

Rethinking Practical and Efficient Quantization Calibration for Vision-Language Models

Zhenhao Shang, Haizhao Jing, Guoting Wei et al. (+4 more)

Post-training quantization (PTQ) is a primary approach for deploying large language models without fine-tuning, and the quantized performance is often strongly affected by the calibration in PTQ. By contrast, in vision-language models (VLMs), substantial differences between visual and text tokens in their activation distributions and sensitivities to quantization error pose significant challenges for effective calibration during PTQ. In this work, we rethink what PTQ calibration should align with in VLMs and propose the Token-level Importance-aware Layer-wise Quantization framework (TLQ). Guided by gradient information, we design a token-level importance integration mechanism for quantization error, and use it to construct a token-level calibration set, enabling a more fine-grained calibration strategy. Furthermore, TLQ introduces a multi-GPU, quantization-exposed layer-wise calibration scheme. This scheme keeps the layer-wise calibration procedure consistent with the true quantized inference path and distributes the complex layer-wise calibration workload across multiple RTX3090 GPUs, thereby reducing reliance on the large memory of A100 GPUs. TLQ is evaluated across two models, three model scales, and two quantization settings, consistently achieving performance improvements across all settings, indicating its strong quantization stability. The code will be released publicly.
Read the full abstract

All authors Zhenhao Shang, Haizhao Jing, Guoting Wei, Haokui Zhang, Rong Xiao, Jianqing Gao, Peng Wang

Computer Vision

Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video

Zihui Gao, Ke Liu, Donny Y. Chen et al. (+5 more)

Geometric foundation models show promise in 3D reconstruction. However, their progress is severely constrained by the scarcity of diverse, large-scale 3D annotations. While static-scene Internet videos are abundant and diverse, utilizing them as a scaling source for geometric learning is challenging due to the absence of ground-truth geometry and the presence of observational noise. To address this, we propose SAGE, a framework for Scalable Adaptation of GEometric foundation models from raw video streams. SAGE leverages a hierarchical mining pipeline to transform videos into training trajectories and hybrid supervisions: (1) Informative training trajectory selection; (2) Sparse Geometric Anchoring via SfM point clouds for global structural guidance; and (3) Dense Differentiable Consistency via 3D Gaussian rendering for multi-view constraints. Besides, we also introduce a regularization strategy that replays a small fraction of supervised data to prevent catastrophic forgetting. Applied to two architecturally distinct backbones, SAGE reduces Chamfer Distance on unseen benchmarks (7Scenes, TUM-RGBD, Matterport3D) by 20-42% with MV-DUSt3R and consistently improves VGGT. SAGE establishes Internet video as a viable and scalable adaptation source for geometric foundation models. Code is available at https://github.com/aim-uofa/SAGE.
Read the full abstract

All authors Zihui Gao, Ke Liu, Donny Y. Chen, Duochao Shi, Guosheng Lin, Jia-Wang Bian, Hao Chen, Chunhua Shen

Computer Vision · Cross-listed from cs.RO

Research on a Camera Position Measurement Method based on a Parallel Perspective Error Transfer Model

Ning Hu, Shuai Li and Jindong Tan

Camera pose estimation from sparse correspondences is a fundamental problem in geometric computer vision and remains particularly challenging in near-field scenarios, where strong perspective effects and heterogeneous measurement noise can significantly degrade the stability of analytic PnP solutions. In this paper, we present a geometric error propagation framework for camera pose estimation based on a parallel perspective approximation. By explicitly modeling how image measurement errors propagate through perspective geometry, we derive an error transfer model that characterizes the relationship between feature point distribution, camera depth, and pose estimation uncertainty. Building on this analysis, we develop a pose estimation method that leverages parallel perspective initialization and error-aware weighting within a Gauss-Newton optimization scheme, leading to improved robustness in proximity operations. Extensive experiments on both synthetic data and real-world images, covering diverse conditions such as strong illumination, surgical lighting, and underwater low-light environments, demonstrate that the proposed approach achieves accuracy and robustness comparable to state-of-the-art analytic and iterative PnP methods, while maintaining high computational efficiency. These results highlight the importance of explicit geometric error modeling for reliable camera pose estimation in challenging near-field settings.
Read the full abstract

Computer Vision

WristMIR: Coarse-to-Fine Region-Aware Retrieval of Pediatric Wrist Radiographs with Radiology Report-Driven Learning

Mert Sonmezer, Serge Vasylechko, Duygu Atasoy et al. (+2 more)

Retrieving wrist radiographs with analogous fracture patterns is challenging because clinically important cues are subtle, highly localized and often obscured by overlapping anatomy or variable imaging views. Progress is further limited by the scarcity of large, well-annotated datasets for case-based medical image retrieval. We introduce WristMIR, a region-aware pediatric wrist radiograph retrieval framework that leverages dense radiology reports and bone-specific localization to learn fine-grained, clinically meaningful image representations without any manual image-level annotations. Using MedGemma-based structured report mining to generate both global and region-level captions, together with pre-processed wrist images and bone-specific crops of the distal radius, distal ulna, and ulnar styloid, WristMIR jointly trains global and local contrastive encoders and performs a two-stage retrieval process: (1) coarse global matching to identify candidate exams, followed by (2) region-conditioned reranking aligned to a predefined anatomical bone region. WristMIR improves retrieval performance over strong vision-language baselines, raising image-to-text Recall@5 from 0.82% to 9.35%. Its embeddings also yield stronger fracture classification (AUROC 0.949, AUPRC 0.953). In region-aware evaluation, the two-stage design markedly improves retrieval-based fracture diagnosis, increasing mean $F_1$ from 0.568 to 0.753, and radiologists rate its retrieved cases as more clinically relevant, with mean scores rising from 3.36 to 4.35. These findings highlight the potential of anatomically guided retrieval to enhance diagnostic reasoning and support clinical decision-making in pediatric musculoskeletal imaging. The source code is publicly available at https://github.com/quin-med-harvard-edu/WristMIR.
Read the full abstract

All authors Mert Sonmezer, Serge Vasylechko, Duygu Atasoy, Seyda Ertekin, Sila Kurugol

Computer Vision

Thinking in Structures: Evaluating Spatial Intelligence in Constraint-Governed Spaces

Chen Yang, Guanxin Lin, Youquan He et al. (+10 more)

Spatial intelligence is crucial for vision–language models (VLMs), yet many scene-centric benchmarks evaluate unconstrained environments where a single image may admit multiple plausible 3D interpretations. We introduce SSI-Bench, a VQA benchmark for Structure-Centric Spatial Reasoning (SCSR) in constraint-governed spaces. Built from complex real-world 3D structures, it uses structural constraints from geometry, topology, and physical feasibility to make component relations more determinate from visual evidence. The benchmark contains 1,000 ranking questions spanning geometric and topological reasoning, where correct ordering requires resolving all candidate-wise 3D relations, imposing stronger demands on spatial understanding. It is created through a fully human-centered pipeline with over 400 researcher-hours of image curation, component annotation, and question design. Evaluating 31 VLMs reveals a large gap to humans: the best open-source model achieves 22.2% accuracy and the strongest closed-source model reaches 33.6%, while humans score 91.6%. Further results show that chain-of-thought reasoning brings only marginal gains, and error analysis reveals fundamental limitations in current models' spatial understanding within constraint-governed spaces. Project page: https://ssi-bench.github.io.
Read the full abstract

All authors Chen Yang, Guanxin Lin, Youquan He, Peiyao Chen, Guanghe Liu, Yufan Mo, Zhouyuan Xu, Linhao Wang, Guohui Zhang, Zihang Zhang, Shenxiang Zeng, Chen Wang, Jiansheng Fan

Computer Vision

Recovering 3D Shapes from Ultra-Fast Motion-Blurred Images

Fei Yu, Shudan Guo, Shiqing Xin et al. (+3 more)

We consider the problem of 3D shape recovery from ultra-fast motion-blurred images. While 3D reconstruction from static images has been extensively studied, recovering geometry from extreme motion-blurred images remains challenging. Such scenarios frequently occur in both natural and industrial settings, such as fast-moving objects in sports (e.g., balls) or rotating machinery, where rapid motion distorts object appearance and makes traditional 3D reconstruction techniques like Multi-View Stereo (MVS) ineffective. In this paper, we propose a novel inverse rendering approach for shape recovery from ultra-fast motion-blurred images. While conventional rendering techniques typically synthesize blur by averaging across multiple frames, we identify a major computational bottleneck in the repeated computation of barycentric weights. To address this, we propose a fast barycentric coordinate solver, which significantly reduces computational overhead and achieves a speedup of up to 4.57x, enabling efficient and photorealistic simulation of high-speed motion. Crucially, our method is fully differentiable, allowing gradients to propagate from rendered images to the underlying 3D shape, thereby facilitating shape recovery through inverse rendering. We validate our approach on two representative motion types: rapid translation and rotation. Experimental results demonstrate that our method enables efficient and realistic modeling of ultra-fast moving objects in the forward simulation. Moreover, it successfully recovers 3D shapes from 2D imagery of objects undergoing extreme translational and rotational motion, advancing the boundaries of vision-based 3D reconstruction. Project page: https://maxmilite.github.io/rec-from-ultrafast-blur/
Read the full abstract

All authors Fei Yu, Shudan Guo, Shiqing Xin, Beibei Wang, Haisen Zhao, Wenzheng Chen

Computer Vision

Geometry-Aware Rotary Position Embedding for Consistent Video World Model

Chendong Xiang, Jiajun Liu, Jintao Zhang et al. (+7 more)

Predictive world models that simulate future observations under explicit camera control are fundamental to interactive AI. Despite rapid advances, current systems lack spatial persistence: they fail to maintain stable scene structures over long trajectories, frequently hallucinating details when cameras revisit previously observed locations. We identify that this geometric drift stems from reliance on screen-space positional embeddings, which conflict with the projective geometry required for 3D consistency. We introduce ViewRope, a geometry-aware encoding that injects camera-ray directions directly into video transformer self-attention layers. By parameterizing attention with relative ray geometry rather than pixel locality, ViewRope provides a model-native inductive bias for retrieving 3D-consistent content across temporal gaps. We further propose Geometry-Aware Frame-Sparse Attention, which exploits these geometric cues to selectively attend to relevant historical frames, improving efficiency without sacrificing memory consistency. We also present ViewBench, a diagnostic suite measuring loop-closure fidelity and geometric drift. Our results demonstrate that ViewRope substantially improves long-term consistency while reducing computational costs.
Read the full abstract

All authors Chendong Xiang, Jiajun Liu, Jintao Zhang, Xiao Yang, Zhengwei Fang, Shizun Wang, Zijun Wang, Yingtian Zou, Hang Su, Jun Zhu

Computer Vision

VFace: A Training-Free Approach for Diffusion-Based Video Face Swapping

Sanoojan Baliah, Yohan Abeysinghe, Rusiru Thushara et al. (+4 more)

We present a training-free, plug-and-play method, namely VFace, for high-quality face swapping in videos. It can be seamlessly integrated with image-based face swapping approaches built on diffusion models. First, we introduce a Frequency Spectrum Attention Interpolation technique to facilitate generation and intact key identity characteristics. Second, we achieve Target Structure Guidance via plug-and-play attention injection to better align the structural features from the target frame to the generation. Third, we present a Flow-Guided Attention Temporal Smoothening mechanism that enforces spatiotemporal coherence without modifying the underlying diffusion model to reduce temporal inconsistencies typically encountered in frame-wise generation. Our method requires no additional training or video-specific fine-tuning. Extensive experiments show that our method significantly enhances temporal consistency and visual fidelity, offering a practical and modular solution for video-based face swapping. Our code is available at https://github.com/Sanoojan/VFace.
Read the full abstract

All authors Sanoojan Baliah, Yohan Abeysinghe, Rusiru Thushara, Khan Muhammad, Abhinav Dhall, Karthik Nandakumar, Muhammad Haris Khan

Computer Vision

SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models

Weijiang Lv, Yaoxuan Feng, Xiaobo Xia et al. (+4 more)

Chain-of-Thought reasoning is widely used to improve the interpretability of multimodal large language models (MLLMs), yet the faithfulness of the generated reasoning traces remains unclear. Prior work has mainly focused on perceptual hallucinations, leaving reasoning level unfaithfulness underexplored. To isolate faithfulness from linguistic priors, we introduce SPD-Faith Bench, a diagnostic benchmark based on fine-grained image difference reasoning that enforces explicit visual comparison. Evaluations on state-of-the-art MLLMs reveal two systematic failure modes, perceptual blindness and perception-reasoning dissociation. We trace these failures to decaying visual attention and representation shifts in the residual stream. Guided by this analysis, we propose SAGE, a train-free visual evidence-calibrated framework that improves visual routing and aligns reasoning with perception. Our results highlight the importance of explicitly evaluating faithfulness beyond response correctness. Our benchmark and codes are available at https://github.com/Johanson-colab/SPD-Faith-Bench.
Read the full abstract

All authors Weijiang Lv, Yaoxuan Feng, Xiaobo Xia, Jiayu Wang, Yan Jing, Wenchao Chen, Bo Chen

Computer Vision

Open-Text Aerial Detection: A Unified Framework For Aerial Visual Grounding And Detection

Guoting Wei, Xia Yuan, Yang Zhou et al. (+6 more)

Open-Vocabulary Aerial Detection (OVAD) and Remote Sensing Visual Grounding (RSVG) have emerged as two key paradigms for aerial scene understanding. However, each paradigm suffers from inherent limitations when operating in isolation: OVAD is restricted to coarse category-level semantics, while RSVG is structurally limited to single-target localization. These limitations prevent existing methods from simultaneously supporting rich semantic understanding and multi-target detection. To address this, we propose OTA-Det, the first unified framework that bridges both paradigms into a cohesive architecture. Specifically, we introduce a task reformulation strategy that unifies task objectives and supervision mechanisms, enabling joint training across datasets from both paradigms with dense supervision signals. Furthermore, we propose a dense semantic alignment strategy that establishes explicit correspondence at multiple granularities, from holistic expressions to individual attributes, enabling fine-grained semantic understanding. To ensure real-time efficiency, OTA-Det builds upon the RT-DETR architecture, extending it from closed-set detection to open-text detection by introducing several high efficient modules, achieving state-of-the-art performance on six benchmarks spanning both OVAD and RSVG tasks while maintaining real-time inference at 34 FPS.
Read the full abstract

All authors Guoting Wei, Xia Yuan, Yang Zhou, Haizhao Jing, Yu Liu, Xianbiao Qi, Chunxia Zhao, Haokui Zhang, Rong Xiao

Computer Vision

Back to Physics: Operator-Guided Generative Paths for SMS MRI Reconstruction

Zhibo Chen, Yu Guan, Yajuan Huang et al. (+5 more)

Simultaneous multi-slice (SMS) imaging with in-plane undersampling enables highly accelerated MRI but yields a strongly coupled inverse problem with deterministic inter-slice interference and missing k-space data. Most diffusion-based reconstructions are formulated around Gaussian-noise corruption and rely on additional consistency steps to incorporate SMS physics, which can be mismatched to the operator-governed degradations in SMS acquisition. We propose an operator-guided framework that models the degradation trajectory using known acquisition operators and inverts this process via deterministic updates. Within this framework, we introduce an operator-conditional dual-stream interaction network (OCDI-Net) that explicitly disentangles target-slice content from inter-slice interference and predicts structured degradations for operator-aligned inversion, and we instantiate reconstruction as a two-stage chained inference procedure that performs SMS slice separation followed by in-plane completion. Experiments on fastMRI brain data and prospectively acquired in vivo diffusion MRI data demonstrate improved fidelity and reduced slice leakage over conventional and learning-based SMS reconstructions.
Read the full abstract

All authors Zhibo Chen, Yu Guan, Yajuan Huang, Chaoqi Chen, XiangJi, Qiuyun Fan, Dong Liang, Qiegen Liu

Computer Vision · Cross-listed from eess.IV

DINO-Mix: Distilling Foundational Knowledge with Cross-Domain CutMix for Semi-supervised Class-imbalanced Medical Image Segmentation

Xinyu Liu and Guolei Sun

Semi-supervised learning (SSL) has emerged as a critical paradigm for medical image segmentation, mitigating the immense cost of dense annotations. However, prevailing SSL frameworks are fundamentally "inward-looking", recycling information and biases solely from within the target dataset. This design triggers a vicious cycle of confirmation bias under class imbalance, leading to the catastrophic failure to recognize minority classes. To dismantle this systemic issue, we propose a paradigm shift to a multi-level "outward-looking" framework. Our primary innovation is Foundational Knowledge Distillation (FKD), which looks outward beyond the confines of medical imaging by introducing a pre-trained visual foundation model, DINOv3, as an unbiased external semantic teacher. Instead of trusting the student's biased high confidence, our method distills knowledge from DINOv3's robust understanding of high semantic uniqueness, providing a stable, cross-domain supervisory signal that anchors the learning of minority classes. To complement this core strategy, we further look outward within the data by proposing Progressive Imbalance-aware CutMix (PIC), which creates a dynamic curriculum that adaptively forces the model to focus on minority classes in both labeled and unlabeled subsets. This layered strategy forms our framework, DINO-Mix, which breaks the vicious cycle of bias and achieves remarkable performance on challenging semi-supervised class-imbalanced medical image segmentation benchmarks Synapse and AMOS.
Read the full abstract

Computer Vision

Out of the box age estimation through facial imagery: A Comprehensive Benchmark of Vision-Language Models vs. out-of-the-box Traditional Architectures

Simiao Ren, Xingyu Shen, Ankit Raj et al. (+7 more)

Facial age estimation plays a critical role in content moderation, age verification, and deepfake detection. However, no prior benchmark has systematically compared modern vision-language models (VLMs) with specialized age estimation architectures. We present the first large-scale cross-paradigm benchmark, evaluating 34 models - 22 specialized architectures with publicly available pretrained weights and 12 general-purpose VLMs - across eight standard datasets (UTKFace, IMDB-WIKI, MORPH, AFAD, CACD, FG-NET, APPA-REAL, and AgeDB), totaling 1,100 test images per model. Our key finding is striking: zero-shot VLMs significantly outperform most specialized models, achieving an average mean absolute error (MAE) of 5.65 years compared to 9.88 years for non-LLM models. The best-performing VLM (Gemini 3 Flash Preview, MAE 4.32) surpasses the strongest non-LLM model (MiVOLO, MAE 5.10) by 15%. MiVOLO - unique in combining face and body features using Vision Transformers - is the only specialized model that remains competitive with VLMs. We further analyze age verification at the 18-year threshold and find that most non-LLM models exhibit false adult rates between 39% and 100% for minors, whereas VLMs reduce this to 16%-29%. Additionally, coarse age binning (8-9 classes) consistently increases MAE beyond 13 years. Stratified analysis across 14 age groups reveals that all models struggle most at extreme ages (under 5 and over 65). Overall, these findings challenge the assumption that task-specific architectures are necessary for high-performance age estimation and suggest that future work should focus on distilling VLM capabilities into efficient specialized models.
Read the full abstract

All authors Simiao Ren, Xingyu Shen, Ankit Raj, Albert Dai, Caroline Zhang, Yuan Xu, Zexi Chen, Siqi Wu, Chen Gong, Yuxin Zhang

Computer Vision

How well are open sourced AI-generated image detection models out-of-the-box: A comprehensive benchmark study

Simiao Ren, Yuchen Zhou, Xingyu Shen et al. (+7 more)

As AI-generated images proliferate across digital platforms, reliable detection methods have become critical for combating misinformation and maintaining content authenticity. While numerous deepfake detection methods have been proposed, existing benchmarks predominantly evaluate fine-tuned models, leaving a critical gap in understanding out-of-the-box performance – the most common deployment scenario for practitioners. We present the first comprehensive zero-shot evaluation of 16 state-of-the-art detection methods, comprising 23 pretrained detector variants (due to multiple released versions of certain detectors), across 12 diverse datasets, comprising 2.6~million image samples spanning 291 unique generators including modern diffusion models. Our systematic analysis reveals striking findings: (1)~no universal winner exists, with detector rankings exhibiting substantial instability (Spearman~$\rho$: 0.01 – 0.87 across dataset pairs); (2)~a 37~percentage-point performance gap separates the best detector (75.0% mean accuracy) from the worst (37.5%); (3)~training data alignment critically impacts generalization, causing up to 20–60% performance variance within architecturally identical detector families; (4)~modern commercial generators (Flux~Dev, Firefly~v4, Midjourney~v7) defeat most detectors, achieving only 18–30% average accuracy; and (5)~we identify three systematic failure patterns affecting cross-dataset generalization. Statistical analysis confirms significant performance differences between detectors (Friedman test: $\chi^2$=121.01, $p<10^{-16}$, Kendall~$W$=0.524). Our findings challenge the “one-size-fits-all” detector paradigm and provide actionable deployment guidelines, demonstrating that practitioners must carefully select detectors based on their specific threat landscape rather than relying on published benchmark performance.
Read the full abstract

All authors Simiao Ren, Yuchen Zhou, Xingyu Shen, Kidus Zewde, Tommy Duong, George Huang, Hatsanai Tiangratanakul, Tsang Ng, En Wei, Jiayu Xue

Computer Vision

VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos

Wenqi Liu, Yunxiao Wang, Shijie Ma et al. (+14 more)

In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance and increased hallucinations. To address this, recent agentic thinking-with-videos paradigms have emerged, adopting a localize-clip-answer pipeline in which the model actively identifies relevant video segments, performs dense sampling within those clips, and then produces answers. However, existing methods remain inefficient, suffer from weak localization, and adhere to rigid workflows. To solve these issues, we propose VideoTemp-o3, a unified agentic thinking-with-videos framework that jointly models video grounding and question answering. VideoTemp-o3 exhibits strong localization capability, supports on-demand clipping, and can refine inaccurate localizations. Specifically, in the supervised fine-tuning stage, we design a unified masking mechanism that encourages exploration while preventing noise. For reinforcement learning, we introduce dedicated rewards to mitigate reward hacking. Besides, from the data perspective, we develop an effective pipeline to construct high-quality long video grounded QA data, along with a corresponding benchmark for systematic evaluation across various video durations. Experimental results demonstrate that our method achieves remarkable performance on both long video understanding and grounding.
Read the full abstract

All authors Wenqi Liu, Yunxiao Wang, Shijie Ma, Meng Liu, Qile Su, Tianke Zhang, Haonan Fan, Changyi Liu, Kaiyu Jiang, Jiankang Chen, Kaiyu Tang, Bin Wen, Fan Yang, Tingting Gao, Han Li, Yinwei Wei, Xuemeng Song

Computer Vision

UCATSC: Uncertainty-Aware Constrained Traffic Signal Control Under Vision-Based Partial Observability

Jayawant Bodagala and Balaji Bodagala

Camera-based adaptive traffic signal control is inherently partially observable: detections can be missed, vehicle speeds and distances can be noisy, and a phase-change decision becomes temporally irreversible once yellow onset is initiated. This paper presents UCATSC, an interpretable uncertainty-aware constrained decision layer for vision-based adaptive signal control. UCATSC maintains a reduced movement-level belief state over queue, arrival, and service-age variables; evaluates admissible phase actions through finite-horizon counterfactual rollouts in belief space; and filters candidate actions using predictive dilemma-zone safety and service-age/starvation constraints before execution. The method is evaluated primarily in SUMO using matched seeds, classical baselines, a trained DQN-RL baseline, a safety-masked DQN variant, targeted safety/liveness/uncertainty stress tests, and a three-intersection corridor extension. In the tested scenarios, UCATSC demonstrates competitive mobility performance, eliminates observed dilemma-zone violations for the constrained variants, bounds service age in starvation stress tests, and maintains millisecond-level online runtime. A controlled physical vision testbed is included as supplementary feasibility evidence for the vision-to-belief interface; it is not presented as field validation of safety, emissions, or deployment readiness.
Read the full abstract

Computer Vision

Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion

Haodong Li, Shaoteng Liu, Zhe Lin et al. (+1 more)

Autoregressive (AR) video diffusion models in the Self Forcing family generate a video chunk by chunk, each conditioned on the ones before it, so they can keep rolling out with no preset length. In practice they are trained on short, fixed clips (e.g., 5s). Once a rollout passes this training horizon, the cache fills with self-generated chunks the model never saw in training, and quality degrades: colors oversaturate, identities drift, structures collapse, and motion fades. We frame this failure as a cache-behavior mismatch, a domain shift between the within-horizon caches seen in training and those produced by open-ended testing, and address it with Rolling Sink, a training-free inference-time cache policy. Within the base model's fixed cache budget, Rolling Sink holds the cache close to its stable within-horizon behavior: it restores low-drift content, sliding temporal indices, and evolving semantics, and keeps a small recent context. Attention sink and temporal re-indexing are existing mechanisms. Our contribution is the mismatch formulation, the joint bounded-cache policy, and the Rolling Semantics schedule. On two 5s-trained bases, Self Forcing and Causal Forcing, Rolling Sink attains the best averaged rank on VBench-Long at both 1- and 5-minute rollouts under the same inference setting, at about 0.56% throughput change, and holds GPU memory constant. It also sustains a 30-minute qualitative rollout, 360 times its training horizon. We validate at 1- and 5-minute rollouts and do not claim guaranteed quality at arbitrary duration. Project page: https://rolling-sink.github.io/
Read the full abstract

All authors Haodong Li, Shaoteng Liu, Zhe Lin, Manmohan Chandraker

Computer Vision

PAND: Prompt-Aware Neighborhood Distillation for Lightweight Fine-Grained Visual Classification

Qiuming Luo, Yuebing Li, Feng Li et al. (+1 more)

Distilling knowledge from large Vision-Language Models (VLMs) into lightweight networks is crucial yet challenging in Fine-Grained Visual Classification (FGVC), due to the reliance on fixed prompts and global alignment. To address this, we propose PAND (Prompt-Aware Neighborhood Distillation), a two-stage framework that decouples semantic calibration from structural transfer. First, we incorporate Prompt-Aware Semantic Calibration to generate adaptive semantic anchors. Second, we introduce a neighborhood-aware structural distillation strategy to constrain the student's local decision structure. PAND consistently outperforms state-of-the-art methods on four FGVC benchmarks. Notably, our ResNet-18 student achieves 76.09% accuracy on CUB-200, surpassing the strong baseline VL2Lite by 3.4%. Code is available at https://github.com/LLLVTA/PAND.
Read the full abstract

All authors Qiuming Luo, Yuebing Li, Feng Li, Chang Kong

Computer Vision · Cross-listed from cs.RO

Global Symmetry and Orthogonal Transformations from Geometrical Moment $n$-tuples

Omar Tahri

Detecting symmetry is crucial for effective object grasping for several reasons. Recognizing symmetrical features or axes within an object helps in developing efficient grasp strategies, as grasping along these axes typically results in a more stable and balanced grip, thereby facilitating successful manipulation. This paper employs geometrical moments to identify symmetries and estimate orthogonal transformations, including rotations and mirror transformations, for objects centered at the frame origin. It provides distinctive metrics for detecting symmetries and estimating orthogonal transformations, encompassing rotations, reflections, and their combinations. A comprehensive methodology is developed to obtain these functions in n-dimensional space, specifically moment \( n \)-tuples. Extensive validation tests are conducted on both 2D and 3D objects to ensure the robustness and reliability of the proposed approach. The proposed method is also compared to state-of-the-art work using iterative optimization for detecting multiple planes of symmetry. The results indicate that combining our method with the iterative one yields satisfactory outcomes in terms of the number of symmetry planes detected and computation time.
Read the full abstract

Saturday 7 February

Computer Vision

COOPERTRIM: Adaptive Data Selection for Uncertainty-Aware Cooperative Perception

Shilpa Mukhopadhyay, Amit Roy-Chowdhury and Hang Qiu

Cooperative perception enables autonomous agents to share encoded representations over wireless communication to enhance each other's live situational awareness. However, the tension between the limited communication bandwidth and the rich sensor information hinders its practical deployment. Recent studies have explored selection strategies that share only a subset of features per frame while striving to keep the performance on par. Nevertheless, the bandwidth requirement still stresses current wireless technologies. To fundamentally ease the tension, we take a proactive approach, exploiting the temporal continuity to identify features that capture environment dynamics, while avoiding repetitive and redundant transmission of static information. By incorporating temporal awareness, agents are empowered to dynamically adapt the sharing quantity according to environment complexity. We instantiate this intuition into an adaptive selection framework, COOPERTRIM, which introduces a novel conformal temporal uncertainty metric to gauge feature relevance, and a data-driven mechanism to dynamically determine the sharing quantity. To evaluate COOPERTRIM, we take semantic segmentation and 3D detection as example tasks. Across multiple open-source cooperative segmentation and detection models, COOPERTRIM achieves up to 80.28% and 72.52% bandwidth reduction respectively while maintaining a comparable accuracy. Relative to other selection strategies, COOPERTRIM also improves IoU by as much as 45.54% with up to 72% less bandwidth. Combined with compression strategies, COOPERTRIM can further reduce bandwidth usage to as low as 1.46% without compromising IoU performance. Qualitative results show COOPERTRIM gracefully adapts to environmental dynamics, localization error, and communication latency, demonstrating flexibility and paving the way for real-world deployment.
Read the full abstract

Computer Vision

Explanatory Interactive Machine Learning for Bias Mitigation in Visual Gender Classification

Nathanya Satriani, Djordje Slijepčević, Markus Schedl et al. (+1 more)

Explanatory interactive learning (XIL) enables users to guide model training in machine learning (ML) by providing feedback on the model's explanations, thereby helping it to focus on features that are relevant to the prediction from the user's perspective. In this study, we explore the capability of this learning paradigm to mitigate bias and spurious correlations in visual classifiers, specifically in scenarios prone to data bias, such as gender classification. We investigate two methodologically different state-of-the-art XIL strategies, i.e., CAIPI and Right for the Right Reasons (RRR), as well as a novel hybrid approach that combines both strategies. The results are evaluated quantitatively by comparing segmentation masks with explanations generated using Gradient-weighted Class Activation Mapping (GradCAM) and Bounded Logit Attention (BLA). Experimental results demonstrate the effectiveness of these methods in (i) guiding ML models to focus on relevant image features, particularly when CAIPI is used, and (ii) reducing model bias (i.e., balancing the misclassification rates between male and female predictions). Our analysis further supports the potential of XIL methods to improve fairness in gender classifiers. Overall, the increased transparency and fairness obtained by XIL leads to slight performance decreases with an exception being CAIPI, which shows potential to even improve classification accuracy.
Read the full abstract

All authors Nathanya Satriani, Djordje Slijepčević, Markus Schedl, Matthias Zeppelzauer

Computer Vision

All-Optical Segmentation via Diffractive Neural Networks for Autonomous Driving

Yingjie Li, Daniel Robinson, Weilu Gao et al. (+1 more)

Semantic segmentation and lane detection are crucial tasks in autonomous driving systems. Conventional approaches predominantly rely on deep neural networks (DNNs), which incur high energy costs due to extensive analog-to-digital conversions and large-scale image computations required for low-latency, real-time responses. Diffractive optical neural networks (DONNs) have shown promising advantages over conventional DNNs on digital or optoelectronic computing platforms in energy efficiency. By performing all-optical image processing via light diffraction at the speed of light, DONNs save computation energy costs while reducing the overhead associated with analog-to-digital conversions by all-optical encoding and computing. In this work, we propose a novel all-optical computing framework for RGB image segmentation and lane detection in autonomous driving applications. Our experimental results demonstrate the effectiveness of the DONN system for image segmentation on the CityScapes dataset. Additionally, we conduct case studies on lane detection using a customized indoor track dataset and simulated driving scenarios in CARLA, where we further evaluate the model's generalizability under diverse environmental conditions.
Read the full abstract

All authors Yingjie Li, Daniel Robinson, Weilu Gao, Cunxi Yu

Computer Vision

A hybrid Kolmogorov-Arnold network for medical image segmentation

Deep Bhattacharyya, Ali Ayub and A. Ben Hamza

Medical image segmentation plays a vital role in diagnosis and treatment planning, but remains challenging due to the inherent complexity and variability of medical images, especially in capturing non-linear relationships within the data. We propose U-KABS, a novel hybrid framework that integrates the expressive power of Kolmogorov-Arnold Networks (KANs) with a U-shaped encoder-decoder architecture to enhance segmentation performance. The U-KABS model combines the convolutional and squeeze-and-excitation stage, which enhances channel-wise feature representations, and the KAN Bernstein Spline (KABS) stage, which employs learnable activation functions based on Bernstein polynomials and B-splines. This hybrid design leverages the global smoothness of Bernstein polynomials and the local adaptability of B-splines, enabling the model to effectively capture both broad contextual trends and fine-grained patterns critical for delineating complex structures in medical images. Skip connections between encoder and decoder layers support effective multi-scale feature fusion and preserve spatial details. Evaluated across diverse medical imaging benchmark datasets, U-KABS demonstrates superior performance compared to strong baselines, particularly in segmenting complex anatomical structures.
Read the full abstract

Computer Vision

Semantic-Deviation-Anchored Multi-Branch Fusion for Unsupervised Anomaly Detection and Localization in Unstructured Conveyor-Belt Coal Scenes

Wenping Jin, Yuyang Tang and Li Zhu

Reliable foreign-object anomaly detection and pixel-level localization in conveyor-belt coal scenes are essential for safe and intelligent mining operations. This task is particularly challenging due to the highly unstructured environment: coal and gangue are randomly piled, backgrounds are complex and variable, and foreign objects often exhibit low contrast, deformation, occlusion, resulting in coupling with their surroundings. These characteristics weaken the stability and regularity assumptions that many anomaly detection methods rely on in structured industrial settings, leading to notable performance degradation. To support evaluation and comparison in this setting, we construct CoalAD, a benchmark for unsupervised foreign-object anomaly detection with pixel-level localization in coal-stream scenes. We further propose a complementary-cue collaborative perception framework that extracts and fuses complementary anomaly evidence from three perspectives: object-level semantic composition modeling, semantic-attribution-based global deviation analysis, and fine-grained texture matching. The fused outputs provide robust image-level anomaly scoring and accurate pixel-level localization. Experiments on CoalAD demonstrate that our method outperforms widely used baselines across the evaluated image-level and pixel-level metrics, and ablation studies validate the contribution of each component. The code is available at https://github.com/xjpp2016/USAD.
Read the full abstract

Computer Vision

Process-of-Thought Reasoning for Videos

Jusheng Zhang, Kaitong Cai, Jian Wang et al. (+3 more)

Video understanding requires not only recognizing visual content but also performing temporally grounded, multi-step reasoning over long and noisy observations. We propose Process-of-Thought (PoT) Reasoning for Videos, a framework that makes the reasoning process explicit by structuring video inference into a sequence of lightweight, verifiable steps. PoT interleaves (i) temporal evidence selection, (ii) step-wise state updates, and (iii) constrained answer synthesis, enabling the model to progressively refine hypotheses while maintaining traceability to video evidence. The framework is designed to be model-agnostic and can be plugged into existing vision-language backbones, supporting both closed-book reasoning and evidence-augmented reasoning with external tools. We further introduce a unified representation for PoT traces that aligns intermediate decisions with temporal segments, which improves robustness to distractors and reduces hallucinated explanations. Extensive experiments on standard video reasoning tasks demonstrate that PoT consistently improves factual correctness and temporal grounding, while providing interpretable reasoning traces for diagnosis and downstream use.
Read the full abstract

All authors Jusheng Zhang, Kaitong Cai, Jian Wang, Yongsen Zheng, Kwok-Yan Lam, Keze Wang

Computer Vision

Vision and Language: Novel Representations and Artificial intelligence for Driving Scene Safety Assessment and Autonomous Vehicle Planning

Ross Greer, Maitrayee Keskar, Angel Martinez-Sanchez et al. (+3 more)

Vision-language models (VLMs) have recently emerged as powerful representation learning systems that align visual observations with natural language concepts, offering new opportunities for semantic reasoning in safety-critical autonomous driving. This paper investigates how vision-language representations support driving scene safety assessment and decision-making when integrated into perception, prediction, and planning pipelines. We study three complementary system-level use cases. First, we introduce a lightweight, category-agnostic hazard screening approach leveraging CLIP-based image-text similarity to produce a low-latency semantic hazard signal. This enables robust detection of diverse and out-of-distribution road hazards without explicit object detection or visual question answering. Second, we examine the integration of scene-level vision-language embeddings into a transformer-based trajectory planning framework using the Waymo Open Dataset. Our results show that naively conditioning planners on global embeddings does not improve trajectory accuracy, highlighting the importance of representation-task alignment and motivating the development of task-informed extraction methods for safety-critical planning. Third, we investigate natural language as an explicit behavioral constraint on motion planning using the doScenes dataset. In this setting, passenger-style instructions grounded in visual scene elements suppress rare but severe planning failures and improve safety-aligned behavior in ambiguous scenarios. Taken together, these findings demonstrate that vision-language representations hold significant promise for autonomous driving safety when used to express semantic risk, intent, and behavioral constraints. Realizing this potential is fundamentally an engineering problem requiring careful system design and structured grounding rather than direct feature injection.
Read the full abstract

All authors Ross Greer, Maitrayee Keskar, Angel Martinez-Sanchez, Parthib Roy, Shashank Shriram, Mohan Trivedi

Computer Vision

Looking and Listening Inside and Outside: Multimodal Artificial Intelligence Systems for Driver Safety Assessment and Intelligent Vehicle Decision-Making

Ross Greer, Laura Fleig, Maitrayee Keskar et al. (+9 more)

The looking-in-looking-out (LILO) framework has enabled intelligent vehicle applications that understand both the outside scene and the driver state to improve safety outcomes, with examples in smart airbag deployment, takeover time prediction in autonomous control transitions, and driver attention monitoring. In this research, we propose an augmentation to this framework, making a case for the audio modality as an additional source of information to understand the driver, and in the evolving autonomy landscape, also the passengers and those outside the vehicle. We expand LILO by incorporating audio signals, forming the looking-and-listening inside-and-outside (L-LIO) framework to enhance driver state assessment and environment understanding through multimodal sensor fusion. We evaluate three example cases where audio enhances vehicle safety: supervised learning on driver speech audio to classify potential impairment states (e.g., intoxication), collection and analysis of passenger natural language instructions (e.g., "turn after that red building") to motivate how spoken language can interface with planning systems through audio-aligned instruction data, and limitations of vision-only systems where audio may disambiguate the guidance and gestures of external agents. Datasets include custom-collected in-vehicle and external audio samples in real-world environments. Pilot findings show that audio yields safety-relevant insights, particularly in nuanced or context-rich scenarios where sound is critical to safe decision-making or visual signals alone are insufficient. Challenges include ambient noise interference, privacy considerations, and robustness across human subjects, motivating further work on reliability in dynamic real-world contexts. L-LIO augments driver and scene understanding through multimodal fusion of audio and visual sensing, offering new paths for safety intervention.
Read the full abstract

All authors Ross Greer, Laura Fleig, Maitrayee Keskar, Erika Maquiling, Giovanni Tapia Lopez, Angel Martinez-Sanchez, Parthib Roy, Jake Rattigan, Mira Sur, Alejandra Vidrio, Thomas Marcotte, Mohan Trivedi

Computer Vision

Influence of Geometry, Class Imbalance and Alignment on Reconstruction Accuracy – A Micro-CT Phantom-Based Evaluation

Avinash Kumar K M and Samarth S. Raut

The accuracy of the 3D models created from medical scans depends on imaging hardware, segmentation methods and mesh processing techniques etc. The effects of geometry type, class imbalance, voxel and point cloud alignment on accuracy remain to be thoroughly explored. This work evaluates the errors across the reconstruction pipeline and explores the use of voxel and surface-based accuracy metrics for different segmentation algorithms and geometry types. A sphere, a facemask, and an AAA were printed using the SLA technique and scanned using a micro-CT machine. Segmentation was performed using GMM, Otsu and RG based methods. Segmented and reference models aligned using the KU algorithm, were quantitatively compared to evaluate metrics like Dice and Jaccard scores, precision. Surface meshes were registered with reference meshes using an ICP-based alignment process. Metrics like chamfer distance, and average Hausdorff distance were evaluated. The Otsu method was found to be the most suitable method for all the geometries. AAA yielded low overlap scores due to its small wall thickness and misalignment. The effect of class imbalance on specificity was observed the most for AAA. Surface-based accuracy metrics differed from the voxel-based trends. The RG method performed best for sphere, while GMM and Otsu perform better for AAA. The facemask surface was most error-prone, possibly due to misalignment during the ICP process. Segmentation accuracy is a cumulative sum of errors across different stages of the reconstruction process. High voxel-based accuracy metrics may be misleading in cases of high class imbalance and sensitivity to alignment. The Jaccard index is found to be more stringent than the Dice and more suitable for accuracy assessment for thin-walled structures. Voxel and point cloud alignment should be ensured to make any reliable assessment of the reconstruction pipeline.
Read the full abstract

Computer Vision

From Dead Pixels to Editable Slides: Infographic Reconstruction into Native Google Slides via Vision-Language Region Understanding

Leonardo Gonzalez

Infographics are widely used to communicate information with a combination of text, icons, and data visualizations, but once exported as images their content is locked into pixels, making updates, localization, and reuse expensive. We describe Images2Slides, an API-based pipeline that converts a static infographic (PNG/JPG) into a native, editable Google Slides slide by extracting a region-level specification with a vision-language model (VLM), mapping pixel geometry into slide coordinates, and recreating elements using the Google Slides batch update API. The system is model-agnostic and supports multiple VLM backends via a common JSON region schema and deterministic postprocessing. On a controlled benchmark of 29 programmatically generated infographic slides with known ground-truth regions, Images2Slides achieves an overall element recovery rate of $0.989\pm0.057$ (text: $0.985\pm0.083$, images: $1.000\pm0.000$), with mean text transcription error $\mathrm{CER}=0.033\pm0.149$ and mean layout fidelity $\mathrm{IoU}=0.364\pm0.161$ for text regions and $0.644\pm0.131$ for image regions. We also highlight practical engineering challenges in reconstruction, including text size calibration and non-uniform backgrounds, and describe failure modes that guide future work.
Read the full abstract