Peer Revenue Fully funded

Papers

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

Computer Science Computer Vision

cs.CV Watch Computer Vision

Thursday 2 July

Computer Vision

Signal Structure-Aware Gaussian Splatting for Large-Scale Scene Reconstruction

Weiyi Xue, Fan Lu, Chi Zhang et al. (+6 more)

3D Gaussian Splatting has demonstrated remarkable potential in novel view synthesis. In contrast to small-scale scenes, large-scale scenes inevitably contain sparsely observed regions with excessively sparse initial points. In this case, supervising Gaussians initialized from low-frequency sparse points with high-frequency images often induces uncontrolled densification and redundant primitives, degrading both efficiency and quality. Intuitively, this issue can be mitigated with scheduling strategies, which can be categorized into two paradigms: modulating target signal frequency via densification and modulating sampling frequency via image resolution. However, previous scheduling strategies are primarily hardcoded, failing to perceive the convergence behavior of scene frequency. To address this, we reframe the scene reconstruction problem from the perspective of signal structure recovery and propose SIG, a novel scheduler that synchronizes image supervision with Gaussian frequencies. Specifically, we derive the average sampling frequency and bandwidth of 3D representations, and then regulate the training image resolution and the Gaussian densification process based on scene frequency convergence. Furthermore, we introduce Sphere-Constrained Gaussians, which leverage the spatial prior of initialized point clouds to control Gaussian optimization. Our framework enables frequency-consistent, geometry-aware, and floater-free training, achieving state-of-the-art performance by a substantial margin in both efficiency and rendering quality in large-scale scenes. The code is available at: https://github.com/weiyixue999/Signal_Structure_Aware_Gaussian
Read the full abstract

All authors Weiyi Xue, Fan Lu, Chi Zhang, Tianhang Wang, Sanqing Qu, Zehan Zheng, Boyuan Zheng, Junqiao Zhao, Guang Chen

Computer Vision

ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning

Xuanhua He, Jiaxin Xie, Mingzhe Zheng et al. (+1 more)

Monocular video depth estimation requires temporal consistency, geometric accuracy, and generalization across diverse scenarios, yet existing methods struggle to achieve all three simultaneously. Discriminative models excel at per-frame accuracy but suffer from temporal drift due to limited context windows, while generative methods improve consistency and generalization at the cost of extensive training data (10M+ samples) and lack of geometric precision. In response to these issues, we introduce ICDepth, a framework that adapts pre-trained text-to-video diffusion transformers for video depth estimation via In-Context Conditioning (ICC), leveraging their rich spatial-temporal priors. To address key challenges in transferring ICC from generation to dense prediction, we propose: (1)~SAND-Attention, which ensures precise spatial-temporal alignment via shared RoPE and enforces unidirectional attention to prevent noise contamination; (2)~SRFM, which injects DINOv2 semantic and resolution priors to enhance geometric precision. ICDepth achieves state-of-the-art results on multiple benchmarks with remarkable data efficiency, trained on only 0.8M frames ($6$–$13\times$ less than competing generative methods), while demonstrating strong zero-shot generalization to diverse domains.
Read the full abstract

All authors Xuanhua He, Jiaxin Xie, Mingzhe Zheng, Qifeng Chen

Computer Vision

HistoSeg++: Delving deeper with attention and multiscale feature fusion for biomarker segmentation

Saad Wazir, Rao Faizan and Daeyoung Kim

Segmentation of biomarkers in medical images is frequently viewed as a first step towards medical image analysis in any bioinformatics or biomedical application. Despite progress, existing methods still struggle to capture information at multiple scales and to perform upsampling effectively across different datasets. These shortcomings often result in suboptimal generalization capabilities. Recently, architectures belonging to the Nested-UNet family excel in capturing multiscale contextual information and upsample them effectively. In this work, We propose a novel Nested-UNet architecture that effectively captures multi-scale contextual information. It includes inner and outer attention units to enhance focus during upsampling, along with channel-wise feature recalibration using squeeze-and-excitation modules, leading to improved segmentation performance. Additionally, the architecture integrates an edge-aware loss to emphasize boundary accuracy by assigning greater importance to edge regions. Tested extensively on three publicly available benchmark datasets. Our method demonstrates a generalization performance superior to existing Nested-UNet methods. Code: https://github.com/saadwazir/histosegplusplus
Read the full abstract

Computer Vision

Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning

Chen Zhao, Jiajun Ma, Qilong Huang et al. (+6 more)

While Multimodal Large Language Models (MLLMs) have advanced video understanding, achieving precise temporal and cross-modal alignment in audiovisual video captioning remains a formidable challenge. Most existing approaches suffer from modality detachment and temporal incoherence, failing to accurately bind auditory events to visual entities or capture complex causal dynamics. To address these deficiencies, we propose TCA-Captioner, a framework specifically engineered to enhance Temporal and Cross-Modal Alignment for audiovisual video captioning. We first introduce the Observer-Checker-Corrector (OCC) framework, an iterative refinement strategy that generates high-fidelity, meticulously grounded training data. Leveraging a curated high-density human interaction dataset, TCA-Captioner is optimized to model sophisticated audiovisual interactions. Furthermore, we present TCA-Bench, a diagnostic benchmark utilizing a Decoupled Evaluation Protocol to isolate and quantify model proficiency in audiovisual binding and temporal relational reasoning. Extensive experiments demonstrate that TCA-Captioner sets a new standard for temporally-coherent and synchronized audiovisual narratives.
Read the full abstract

All authors Chen Zhao, Jiajun Ma, Qilong Huang, Tiehan Fan, Hongyu Li, Zhuoliang Kang, Xiaoming Wei, Jian Yang, Ying Tai

Computer Vision

Unified Panoramic-Gaussian Representation for Monocular 4D Scene Synthesis

Yuankun Yang, Yi Wei, Wenyang Zhou et al. (+1 more)

4D scene synthesis from monocular videos has made significant progress in recent years. However, existing methods are typically constrained by view interpolation. As a result, they struggle to infer unseen regions beyond the observed views. In this paper, we reformulate the task as 4D scene synthesis with unseen regions, which extends beyond traditional interpolation settings. Camera-conditioned video generation enables unseen region synthesis by guiding generation along specified cameras. However, these methods lack explicit 3D priors and are optimized with random camera trajectories. This design leads to severe inconsistencies under large trajectory deviations. To address this limitation, we build a unified training and inference framework with panoramic trajectory guidance. While this design improves cross-view consistency, the panoramic representation alone fails to model dynamic content effectively. Object motion in panoramic space introduces scale and shape distortions. To address this, we propose PanoGaussian, a unified Panoramic-Gaussian representation that distills the panoramic representation into an explicit dynamic Gaussian representation to capture dynamic physical priors of the 4D scene. Experiments demonstrate that PanoGaussian achieves consistent 4D scene synthesis even under large viewpoint variations.
Read the full abstract

All authors Yuankun Yang, Yi Wei, Wenyang Zhou, Li Zhang

Computer Vision

Teaching Vision-Language-Action Models What to See and Where to Look

Yuguang Yang, Canyu Chen, Zhewen Tan et al. (+10 more)

Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving. However, existing VLAs' training relies heavily on text-centric visual question answering and chain-of-thought reasoning data, which emphasizes linguistic reasoning rather than action-grounded planning. As a result, the learned representations capture semantic knowledge but lack spatial dependencies crucial for reliable trajectory prediction. We propose DriveTeach-VLA, a framework that explicitly teaches VLAs what to see and where to look. Driving-aware Vision Distillation (DVD) injects driving-specific perceptual priors into the vision encoder, while 2D Trajectory-Guided Prompts (2D-TGP) provide spatial conditioning aligned with feasible driving trajectories. Together, they form a vision-guided learning pipeline: what to see (DVD pretraining) - where to look (TGP-guided SFT) - how to act (TGP-guided GRPO). DriveTeach-VLA achieves the state-of-the-art performance on NAVSIM and nuScenes. Our code is available at: https://github.com/ShivaTeam/DriveTeach-VLA.
Read the full abstract

All authors Yuguang Yang, Canyu Chen, Zhewen Tan, Yizhi Wang, Zichao Feng, Chunyang Liu, Kehua Sheng, Juan Zhang, Linlin Yang, Baochang Zhang, Yan Wang, Bo Zhang, Xianbin Cao

Computer Vision

Domain Generalization via Text-Anchored Information Bottleneck

Eunyi Lyou, Yunjeong Choi, Junho Lee et al. (+1 more)

Visual recognition models often fail when deployed in new environments. Domain Generalization (DG) addresses this by learning representations that remain invariant to environment-specific variations. Recent approaches increasingly rely on large vision-language models, assuming that preserving their expressive visual representations improves robustness. However, we show that such visual expressiveness can instead propagate spurious cues that tie representations to the training environments, hindering invariant learning. We therefore discard visual guidance and instead treat the language embedding space as the primary source of domain invariance, naturally acting as an information bottleneck that preserves core semantics while suppressing domain-specific variations. Extensive experiments across diverse backbones exhibit state-of-the-art performance and further analyze what makes guidance effective for robust generalization. These findings shift the focus of DG from improving representations to designing supervision that enforces invariance.
Read the full abstract

All authors Eunyi Lyou, Yunjeong Choi, Junho Lee, Joonseok Lee

Computer Vision

Plug-and-Play Volumetric Reconstruction for Compressive Sensing Light-Sheet Microscopy

Jianqing Jia, Yi Gong, Xinyuan Zhang et al. (+3 more)

We investigate volumetric reconstruction for compressive sensing light-sheet microscopy (CS-LSM), where fast volumetric imaging is achieved by encoding multiple axial planes into each camera exposure. To recover the underlying volume from highly multiplexed measurements, we propose a plug-and-play (PnP) framework that flexibly incorporates any user-specified denoiser into the reconstruction process. Building on a slice-based formulation, we further introduce an axial-coupled model that exploits correlations between adjacent slices to improve volumetric continuity. For efficient computation, we derive a Woodbury-based update for the data-consistency step in both the slice-based and axial-coupled formulations, and employ a Gauss-Seidel sweep for the denoising step in the axial-coupled model. Under a weakly convex regularization assumption, we establish subsequential convergence of the proposed algorithm. Experiments on synthetic and real zebrafish-heart data demonstrate that the proposed framework successfully recovers cellular structures from compressed measurements, and provide practical insights into the comparative performance of commonly used denoisers within the PnP framework under the CS-LSM setup.
Read the full abstract

All authors Jianqing Jia, Yi Gong, Xinyuan Zhang, Jichen Chai, Yichen Ding, Yifei Lou

Computer Vision

Boosting Ultrasound Image Classification via Attribute-Guided Dual-Branch Framework

Bo Zhao, Yapeng Li, Juhua Liu et al. (+1 more)

Ultrasound image classification is essential for computer-aided diagnosis. However, current methods often neglect clinical priors, leading to poor generalization in challenging scenarios and a lack of interpretability that limits clinical adoption. To address these issues, we aim to develop a medical-prior module that can be seamlessly integrated into existing pipelines to enhance both diagnostic performance and interpretability. In this paper, we propose an attribute-guided dual-branch framework for ultrasound classification that introduces domain-agnostic medical attribute priors, improving generalization while offering interpretable evidence. Specifically, a baseline branch follows conventional architectures and predicts image categories via a fully connected classifier. An attribute-guided branch injects domain-agnostic attributes as priors and produces human-interpretable decision cues. Finally, an adaptive decision module fuses the two branches in a data-dependent manner to yield the final prediction. Experiments across diverse ultrasound classification tasks demonstrate that our approach can be integrated into multiple backbones and state-of-the-art methods with low overhead, consistently improving accuracy and interpretability. Code is available at: https://github.com/zhaobo253-crypto/AttrGuide.
Read the full abstract

All authors Bo Zhao, Yapeng Li, Juhua Liu, Bo Du

Computer Vision

Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling

Xingyu Zheng, Xianglong Liu, Yifu Ding et al. (+4 more)

Hardware-agnostic strategies for accelerating text-to-image diffusion, such as timestep distillation and feature caching, can reduce inference time without custom kernels or system-level optimization. Among them, multi-resolution generation strategies have recently received broad attention, attaining more than 5x speedup without any training. However, the design of performing upsampling in the latent space, together with the selective modification of partial regions, causes these methods to exhibit noticeable blurring or artifacts. To this end, we propose MrFlow, a training-free multi-resolution acceleration strategy for pretrained flow-matching models built upon a staged low-to-high-resolution pipeline. MrFlow first rapidly generates the main structure at low resolution, then performs super-resolution in the pixel space using a lightweight pretrained GAN-based model, subsequently injects low-strength noise to enable high-frequency resampling, and finally refines the details at high resolution. Quantitative and qualitative results on FLUX.1-dev and Qwen-Image show that MrFlow exploits the quadratic token reduction and reduced step requirement of low-resolution sampling to achieve 10x end-to-end acceleration while keeping OneIG within a 1% gap relative to that before acceleration, significantly surpassing other training-free acceleration strategies, and requiring no training or runtime dynamic identification whatsoever. MrFlow can further be directly combined orthogonally with pre-trained timestep distillation strategies, achieving even higher generation acceleration of up to 25x.
Read the full abstract

All authors Xingyu Zheng, Xianglong Liu, Yifu Ding, Weilun Feng, Junqing Lin, Jinyang Guo, Haotong Qin

Computer Vision

Bridging 3D Gaussians and Semantic Occupancy for Comprehensive Open-Vocabulary Scene Understanding from Unposed Images

Hu Zhu, Bohan Li, Xianda Guo et al. (+5 more)

Comprehensive 3D scene understanding from sparse, unposed images requires a model to recover renderable geometry, open-vocabulary semantics, and free/occupied 3D space without relying on external camera calibration. Recent feed-forward Gaussian methods improve pose-free reconstruction and semantic rendering, but their Gaussian primitives are mainly optimized through image-space objectives and remain weakly constrained in unobserved regions. We propose COVScene, a pose-free semantic Gaussian framework that couples renderable Gaussian primitives with a dense semantic occupancy field through differentiable volumetric lifting. Instead of converting Gaussians to voxels only at evaluation time, COVScene lifts the predicted semantic Gaussians inside the training computation graph, so volumetric regularization provides gradients to Gaussian opacity, geometry, and semantic features. The framework combines a semantic-aware Geometry Transformer, multi-task Gaussian decoding, geometric foundation distillation, and occupancy entropy regularization to support novel view synthesis, open-vocabulary semantic querying, and semantic occupancy prediction within a single representation. Experiments on ScanNet and ScanNet++ show that COVScene maintains competitive rendering quality, improves open-vocabulary segmentation, and achieves stronger semantic occupancy prediction than the self-supervised baseline without direct voxel-level supervision.
Read the full abstract

All authors Hu Zhu, Bohan Li, Xianda Guo, Yanlun Peng, Zheng Zhu, Xin Jin, Wenjun Zeng, Chang Wen Chen

Computer Vision

DRDN: Decoupled Representation Dynamic Network for From-Scratch ViT Class-Incremental Learning

Bingchen Huang, Yifu Chen, Zhiling Wang et al. (+1 more)

Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our analyses suggest that classification supervision alone does not sufficiently preserve task-agnostic shared backbone representations over long incremental sequences. We identify two intertwined challenges: cross-task confusion from sequential training on predominantly current-task data, which biases decision boundaries toward recent tasks; and under-optimized shared representations in the backbone that cap long-term discriminability as tasks accumulate. We propose the Decoupled Representation Dynamic Network (DRDN), which addresses these challenges via two orthogonal mechanisms. For shared backbone representations, DRDN continuously applies masked image modeling (MIM) at every incremental step, with reconstruction gradients routed exclusively through the backbone, encouraging it to retain general visual structure beyond class-discriminative cues. For task-specific discrimination, DRDN employs hierarchical task token expansion across all transformer layers, with a modified per-task attention rule that reduces inter-task interference. We support this design with accuracy degradation analysis and cross-task confusion rate measurements. In the from-scratch ViT CIL setting (no external pretraining), DRDN consistently improves over strong token-expansion baselines with comparable backbone scale. On CIFAR100-B0 (10 steps), DRDN achieves 77.19% average accuracy, outperforming DKT by 1.36 points and DyTox by 3.53 points, with an advantage that grows at longer incremental sequences. Multi-seed validation confirms stability (+/-0.31%). The MIM decoder is active only during training, adding no inference-time parameters or computation.
Read the full abstract

All authors Bingchen Huang, Yifu Chen, Zhiling Wang, Yuanchao Du

Computer Vision

Online Segment 3D Gaussians via Launching Virtual Drones

Liwei Liao, Rongjie Wang and Ronggang Wang

Interactive segmentation of 3D Gaussians offers a compelling opportunity for real-time manipulation of 3D scenes, thanks to the real-time rendering capability of 3D Gaussian Splatting (3DGS). However, existing methods require a time-consuming per-scene setup - typically tens of seconds or even minutes - before interactive segmentation can begin on a raw 3DGS scene. This setup involves multi-view mask preparation, mask lifting, and feature distillation, creating a major bottleneck for online applications. To address this limitation, we aim to completely eliminate the setup stage for interactive 3DGS segmentation while keeping the segmentation time practical (under 1 second). In this work, we present SAGO (Segment Any Gaussians Online), a novel setup-free framework for interactive 3DGS segmentation. By introducing virtual drones, our method reframes the 3D segmentation problem as an online Next-Best-View (NBV) planning task formulated within a Markov process. Extensive experiments demonstrate that SAGO can extract clean 3D assets directly from 3D Gaussians with sub-second latency, thereby enabling a broad range of downstream applications such as object manipulation and scene editing. Moreover, our method achieves over a 50x speedup compared to the previous setup-free 3DGS segmentation frameworks.
Read the full abstract

Computer Vision

Multi-THuMBS: Multi-person Tracking of 3D Human Meshes Beyond Video Shots

Jeongwan On, Muhammad Salman Ali, Muneeb A. Khan et al. (+6 more)

Tracking multi-person 3D human meshes from in-the-wild videos is a highly challenging problem due to complex interactions, frequent occlusions, and severe truncation inherent in unconstrained environments. While recent approaches have improved robustness against these issues, they largely overlook the critical challenge prevalent in real-world footage: frequent shot changes. These abrupt transitions in camera viewpoints often cause existing methods to lose track of human identities and fail in reconstructing temporally coherent trajectories. Although several recent works have explored 3D human mesh tracking under shot changes, they are still limited to single-person scenarios, making them inadequate for real-world videos where multiple people interact and appear simultaneously. To address this limitation, we propose Multi-THuMBS (Multi-person Tracking of 3D Human Meshes Beyond Video Shots) that leverages a state-of-the-art 3D scene prior to reconstruct the two boundary frames in a single shared 3D space. Human meshes are then registered within the shared 3D space, maintaining per-person identity and motion consistency across shot changes. Extensive experiments demonstrate that our approach yields significant improvements in 3D human mesh recovery, camera pose estimation, and identity tracking, thereby ensuring high-fidelity motion reconstruction with consistent identity preservation across shots compared to previous state-of-the-art methods.
Read the full abstract

All authors Jeongwan On, Muhammad Salman Ali, Muneeb A. Khan, Sunwoo Park, Inwoong Moon, Hyung Jin Chang, Jaekwang Kim, Seong Jong Ha, Seungryul Baek

Computer Vision

VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment

Guoyang Xia, Fengfa Li, Hongjin Ji et al. (+4 more)

Vision-language-action models (VLAs) have recently advanced robotic manipulation, yet the effects of different robot-data pre-training paradigms remain difficult to compare because existing models often differ in architecture, data, action space, and evaluation protocol. We present VLAFlow (Vision-Language-Action Flow), a unified flow-matching framework for controlled comparison of VLA training objectives. Using a heterogeneous robot corpus, OXEMix, containing approximately 5,000 hours of data from DROID, OpenX-Embodiment, OpenX-Augmented, and RoboCOIN, we evaluate four paradigms under the same pi0-style architecture, shared VLM backbone, action expert, and 14-dimensional action space: action-only modeling (MindPI), language-supervised co-training (MindLPI), future latent alignment (MindWPI), and their combination (MindLWPI). Experiments on LIBERO, LIBERO-Plus, and SimplerEnv show that action-only pre-training is sensitive to heterogeneous data. In contrast, language supervision helps preserve vision-language generalization, while future latent alignment improves state-transition and action-outcome modeling. By combining both signals, MindLWPI achieves the most stable overall transfer performance across benchmarks. These results suggest a meta-action space view: language and future latent representations provide complementary intermediate constraints that make heterogeneous action supervision smoother and more transferable.
Read the full abstract

All authors Guoyang Xia, Fengfa Li, Hongjin Ji, Lei Ren, Fangxiang Feng, Kun Zhan, Yan Xie

Computer Vision

MVFusion-GS: Motion-Variance Guided Temporal Attention for High-Quality Dynamic Gaussian Splatting

Jianwei Hu, Tingxuan Huang, Hengyu Zhou et al. (+4 more)

3D Gaussian Splatting (3DGS) enables real-time novel view synthesis for static scenes. Extending it to dynamic scenes via deformation fields has recently attracted significant attention, particularly for dynamic scene reconstructionband distractor-free. However, existing deformation networks lack explicit motion awareness: they neither capture long-term motion intensity nor exploit short-term temporal coherence, leading to inaccurate foreground deformation and pseudo-static residuals in the background. We present MVFusion-GS, a method that enhances deformation networks with two complementary motion-aware mechanisms. The Motion-Variance Guided Refinement aggregates per-Gaussian deformation statistics across time to estimate motion variance and uses it to guide dynamic-static separation during deformation prediction. The MotionFormer Temporal Attention module applies Transformer self-attention over neighboring timesteps to model local motion dependencies and improve temporal consistency. Extensive experiments on both dynamic scene reconstruction and distractor-free reconstruction benchmarks demonstrate state-of-the-art performance, showing that explicit motion awareness improves both foreground motion modeling and static background reconstruction.
Read the full abstract

All authors Jianwei Hu, Tingxuan Huang, Hengyu Zhou, Ningna Wang, Xiaohu Guo, Jinshan Lai, Bin Wang

Computer Vision

Mind the Gap: Standard 3DGS Evaluation Primarily Measures Near-Trajectory Interpolation

Gaoxiang Jia and Vikram Appia

Standard MipNeRF360-style 3D Gaussian Splatting (3DGS) evaluation holds out every N-th frame – but these frames have trained neighbors on both sides, so the metric measures near-trajectory interpolation rather than spatial generalization. We introduce a fair matched-count protocol that isolates this effect: both arms train on the same number of images and differ only in whether the holdout is spread evenly (interpolation) or forms a contiguous spatial sector (extrapolation). Our primary finding is a large, consistent interpolation-extrapolation gap of 3~12dB – several times the differences typically reported between competing methods. The gap is robust to training noise, is in two cases large enough to flip a method ranking under multi-seed confirmation, and – crucially – persists across three representation families, including a non-Gaussian volumetric neural radiance field (NeRF), so it reflects spatial coverage rather than any one representation. Diagnostically, it is dominated by a diffuse/geometry-proxy component and tracks each view's angular distance to its nearest training view, a zero-cost signal that also guides capture planning; loss-side regularization yields only marginal gains. Standard holdouts remain useful for near-trajectory rendering but should not, alone, be read as evidence of spatial generalization. Prior work notes protocol sensitivity; ours is, to our knowledge, the first to combine matched-count paired holdout, cross-representation quantification, and a diagnostic analysis Table 1. We describe a spatial-holdout benchmark toolkit with standardized splits and baselines for 16 scenes, which we are preparing for public release.
Read the full abstract

Computer Vision

Boosting Infrared Small Target Detection via Logit-Domain Contrast and Adaptive Shape Refinement

Handong Zeng, Zhengeng Yang, Shuai Zhang et al. (+2 more)

Infrared small target detection (IRSTD) remains challenging due to tiny target size, low signal-to-noise ratio, severe foreground-background imbalance, and blurred boundaries in complex scenes. Existing methods usually rely on post-activation probability-domain supervision for discrimination, where weak targets and strong clutter may produce saturated and close probabilities, limiting weak-target discrimination. Meanwhile, blurred boundaries and halo-like predictions mainly stem from thermal diffusion, tiny target scale, boundary uncertainty, and insufficient explicit contour constraints. To address these issues, we propose Adaptive-Contrastive SLSIoU (AC-SLSIoU), a plug-and-play discriminative and shape-aware loss for IRSTD. Specifically, a Logit-Domain Margin Constraint (LDMC) is introduced to enlarge the response gap between targets and informative hard negatives in the logit space, thereby enhancing weak-target discrimination. Adaptive Boundary Suppression (ABS) applies scale-aware annular penalties to refine target contours and suppress halo-like overflow responses. In addition, False-Alarm Focal Loss assigns larger weights to high-probability negative samples, further penalizing persistent high-confidence false alarms. Without introducing extra inference overhead, the proposed method can be seamlessly integrated into existing detectors and consistently improves both detection accuracy and shape quality. Extensive experiments and cross-backbone evaluations demonstrate the effectiveness, robustness, and generalization ability of the proposed method for infrared small target detection.
Read the full abstract

All authors Handong Zeng, Zhengeng Yang, Shuai Zhang, Shikai Chen, Hongshan Yu

Wednesday 1 July

Computer Vision · Cross-listed from cs.LG

Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions

David R. Wessels, Farhad Ramezanghorbani, Alireza Moradzadeh et al. (+9 more)

Subquadratic alternatives to attention require compromises when applied to multi-dimensional data: standard convolutions lack global receptive fields and input dependency, while recurrent models require rasterizing data such as images, volumes, and partial differential equation (PDE) into an ad-hoc $1\rm D$ scan order that violates their spatial structure. We introduce HyenaND, a subquadratic, global, input-dependent operator that acts directly on the native geometry of multidimensional data through convolutions with implicitly parametrized global, input-dependent multi-dimensional convolutional kernels. Our CUDA implementation, nSubQ, fuses the FFT-convolution path to turn HyenaND's $\mathcal{O}(L \log L)$ scaling into wall-clock speedups. Across long-context genomics, computer vision, medical imaging, and PDE modeling, pure HyenaND stacks match the accuracy of strong attention baselines, while hybrid configurations that interleave HyenaND and attention layers outperform both pure attention and strong recurrence-based hybrids.
Read the full abstract

All authors David R. Wessels, Farhad Ramezanghorbani, Alireza Moradzadeh, David W. Romero, Olivia Viessmann, Maksim Zhdanov, John St. John, Ken Janik, David M Knigge, Yucheng Tang, Erik J Bekkers, Saee Gopal Paliwal

Computer Vision

Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers

Aravind Pradeep, Samira Nazari, Mahdi Taheri et al. (+1 more)

Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformative. Recent adaptive inference methods reduce this cost by selectively compressing tokens or terminating inference early, but combining these mechanisms often causes unstable intermediate representations and accuracy degradation. We introduce Fusion, a unified adaptive inference framework that coordinates token merging, early exiting, and token pruning through a simple staged design: tokens are merged first, confidence is evaluated next, and pruning is applied only to samples that continue inference. This ordering allows the three mechanisms to operate cooperatively rather than competitively. Fusion further includes lightweight routing modules that adapt compression strength to each input and support inference-time adjustment of the accuracy–latency trade-off without retraining. On ImageNet-1k with DeiT-S, Fusion matches or surpasses state-of-the-art adaptive ViT methods at comparable compute budgets while reducing calibration error by up to $4\times$ and inference energy by $48\%$. Experiments across ImageNet-100, CIFAR-100, and ImageNette with multiple ViT backbones demonstrate consistent transferability without dataset-specific tuning.
Read the full abstract

All authors Aravind Pradeep, Samira Nazari, Mahdi Taheri, Christian Herglotz

Computer Vision

Privacy-Preserving Industrial Ergonomics: mmWave-Based Automated REBA Scoring and Pose Estimation

Xuhan Zhang, Zhuangzhuang Dai, Luis J. Mans et al. (+1 more)

Work-related Musculoskeletal Disorders (WMSDs) require continuous ergonomic assessments. While Rapid Entire Body Assessment (REBA) is a gold-standard observation tool, manual monitoring is labor-intensive, and vision-based automation leads to privacy concerns. This paper proposes a novel end-to-end multi-task learning framework for privacy-preserving ergonomic assessment using millimetre-wave (mmWave) radar. A spatio-temporal backbone reconstructs 3D human skeletons, which serves as the biomechanical foundation for a subsequent regression head to generate REBA risk scores. To overcome the sparsity of radar point clouds, we utilise a multi-objective loss function incorporating biomechanical limits and temporal smoothness constraints. Furthermore, we implement an oversampling strategy to address the imbalance of high-risk postures in existing datasets. Experimental results on MMFi dataset demonstrate that our framework achieves a Categorical Accuracy of 77.78% and real-time performance with an inference latency of 5.70 ms. Our method reaches a High-risk REBA MAE of 0.93, which significantly outperforms both direct regression and two-stage pipelines in high-risk scenarios, providing a robust solution for non-invasive industrial ergonomic assessment.
Read the full abstract

All authors Xuhan Zhang, Zhuangzhuang Dai, Luis J. Mans, Victor Chang

Computer Vision

Latent Visual Cache for Video Reasoning

Yongheng Zhang, Zhipeng Xu, Hao Wu et al. (+4 more)

Video reasoning requires Large Multimodal Models (LMMs) to remain grounded in dense evidence, yet existing systems largely adopt "read-once, generate-many" paradigm, in which visual grounding weakens during generation. This phenomenon has been widely observed and is known as Visual Anchoring Decay. To fill this gap, we introduce Latent Video Cache (Latent-VC), a recurrent latent visual cache inserted into the decoder to preserve compact visual memories throughout reasoning. The cache is trained with supervised contrastive cache alignment and vision-grounded GRPO with a latent grounding reward, while maintaining strict train-inference alignment through native decoder hidden states. Built on Qwen3.5-9B, Latent-VC consistently outperforms strong CoT and SFT+GRPO baselines across six video benchmarks, with especially clear gains on grounding-intensive and long-video tasks. In addition, it also achieves higher accuracy with substantially shorter responses, suggesting that latent visual caching improves video reasoning by preserving visual evidence rather than relying on longer textual chains.
Read the full abstract

All authors Yongheng Zhang, Zhipeng Xu, Hao Wu, Yinghui Li, Di Yin, Xing Sun, Philip S. Yu

Computer Vision

DynaWM: A Base-VLA-Guided World Foundation Model for Moving-Object Manipulation

Chongkei Chang and Zhidong Deng

Although vision-language-action (VLA) models have received widespread attention, many challenges remain in manipulating dynamic moving objects. In most existing approaches, end-to-end forward or inverse dynamics models, i.e., world models, are incorporated into high-performance base VLA architectures, which may degrade the performance of well-pretrained base VLA models due to inappropriate fine-tuning. In this paper, we propose DynaWM, a base-VLA-guided world foundation model that adapts to a wide variety of fine-tuned and coarse-tuned base-VLA checkpoints for moving-object manipulation. DynaWM uses a Mamba-3-based action encoder to encode the base action chunk produced by the base VLA into an action-conditioning representation, a V-JEPA 2.1 vision encoder to extract features from multi-view observation history, and a proprioceptive state encoder to encode robotic-arm proprioceptive states. These feature representations jointly condition a flow-matching DiT to regenerate motion-aware action trajectories for moving-object manipulation. For systematic evaluation, we construct the DynaGrasp-32 benchmark, covering six categories of moving-object manipulation tasks, including velocity variation, trajectory variation, and multi-object manipulation, as well as the DynaGrasp-1600 dataset, which consists of 32 scenarios, 1,600 demonstration trajectories, and approximately 1.53M images. For fine-tuned base-VLA checkpoints, DynaWM achieves percentage improvements of 7.19, 45.31, 1.88, and 10.94 over SmolVLA, X-VLA, {\pi}0, and {\pi}0.5, respectively. For coarse-tuned base-VLA checkpoints, performance increases by 35.13, 44.06, 35.69, and 26.13 percentage, respectively. Ablation experiments show that visual encoding enhances success by 27.50%, while reducing success by 45.44% if action conditioning is removed.
Read the full abstract

Computer Vision

CV-DCLR: Causal-Visual Dynamic Label Refinement for Robust Zero-Shot Learning

Can Wang, Jiangnan Li, Mingyu Li et al. (+4 more)

Zero-Shot Learning (ZSL) facilitates knowledge transfer via shared semantic spaces. However, a critical bottleneck in this paradigm is Semantic Entanglement, where visual representations are inevitably conflated with visually similar semantic concepts, such as distinguishing the intrinsic traits of a Wolf from the shared features of a Husky. Existing global alignment methods often indiscriminately maximize correlations between visual and semantic modalities, leading models to overfit spurious similarities rather than capturing distinctive class identities. To address this fundamental limitation, we propose the Causal-Visual Dynamic Label Refinement (CV-DCLR) framework. Unlike traditional approaches that rely on superficial visual statistics, CV-DCLR recalibrates visual-semantic associations via a Dual-Stream Mutual Correction Mechanism. This includes a Visual Likelihood Stream to model observational patterns and a Causal Importance Stream that verifies the structural necessity of candidate prototypes through Counterfactual Intervention. Acting as a logical filter, our adaptive gating mechanism dynamically modulates feature responses to amplify genuine causal traits while suppressing visually plausible but structurally irrelevant distractors. Extensive experiments on the CUB, SUN, and AWA2 benchmarks under a rigorous Semantic Entanglement Injection protocol demonstrate that CV-DCLR significantly outperforms state-of-the-art methods in high-ambiguity scenarios. Specifically, while existing models suffer catastrophic degradation under entanglement, our framework maintains robust performance, effectively disentangling true class identities from semantic confounders.
Read the full abstract

All authors Can Wang, Jiangnan Li, Mingyu Li, Yining Song, Kangrui Ren, Min Gan, Jinfu Fan

Computer Vision

Evaluating Agentic Harness Systems for Autonomous Computational Pathology

Jie Lin, Zongyi Chen, Qiaoling Zheng et al. (+6 more)

Autonomous computational pathology (ACP) converts high-level pathology analysis goals into executable, traceable and clinically bounded workflows. Realizing this capability requires adapting general agentic harness systems to pathology-specific tasks, tools, evidence standards and clinical claim boundaries. We contribute ACP-Bench, a framework that adapts existing harness systems from computational pathology support toward ACP workflow capability. ACP-Bench evaluates 41 pathology workflow tasks, including 24 biomarker, 7 morphology and 10 prognosis tasks spanning 6 body-system groups and 9 endpoint families. The benchmark evaluates 9 models and 3 harness groups (Claude Code, Codex and Open Code), yielding 369 complete trajectories. ACP-Bench evaluates each trajectory across workflow execution, diagnostic performance and clinical-boundary alignment, combining expert-adjudicated process audits, diagnostic assessment and pathologist-validated safety review. Across evaluated systems, workflow initiation, task interpretation and diagnostic reporting were more mature than tool-bound execution, result binding and reflective workflow revision, and formal end-to-end completion remained rare. ACP-Bench provides a reusable standard for auditing whether agentic systems can operationalize pathology workflows before claims of reliable clinical autonomy.
Read the full abstract

All authors Jie Lin, Zongyi Chen, Qiaoling Zheng, Liuyi Wang, Hengyi Jiang, Jiabao Chen, Xiang Liu, Yinghong Yang, Liansheng Wang

Computer Vision

CIPHER: Causal Intervention Pathways for Healthcare Equity and Robustness

Xinyu Jia, Weidong Guo, Wangyuan Zhao et al. (+3 more)

Deep learning models for medical diagnosis frequently exhibit substantial performance disparities across sensitive subgroups (e.g., race, sex), even when average accuracy is high. While generative data augmentation offers a route to mitigate this, existing strategies are suboptimal; they typically address only one or two dependency channels between sensitive attributes and image features. We formalize the medical image formation process via a structural causal model, revealing that sensitive attributes actually influence image content through four distinct pathways-a structural complexity neglected by prior works. Based on this insight, we introduce CIPHER (Causal Intervention Pathways for Healthcare Equity and Robustness), a framework designed to systematically intervene on all four causal paths. To achieve this, CIPHER utilizes a diffusion backbone equipped with classifier-free guidance and null-text inversion. This technical design enables the faithful reconstruction of patient-specific anatomy while allowing for the precise, editable synthesis of counterfactuals required to break sensitive dependency chains. We tested CIPHER using chest X-ray and dermoscopy benchmarks across both standard and shifted data distributions. By employing a multi-pathway intervention strategy, our model reduced worst-group disparities by an average of 35.8% compared to disease-conditioned synthesis baselines, while also improving total diagnostic accuracy
Read the full abstract

All authors Xinyu Jia, Weidong Guo, Wangyuan Zhao, Yi Guo, Zeju Li, Yuanyuan Wang

Computer Vision

An automated method of identifying incorrectly labelled images based on the sequences of loss functions of deep learning networks

Zhipeng Zhang, Wenhui Shou, Wengting Ma et al. (+5 more)

Deep learning is widely applied in medical image analysis, but up to 10% of manually labelled images may be incorrect, degrading model performance. This paper proposes an automated method to identify incorrectly labelled medical images by analyzing sequences of loss functions from deep learning classification networks over multiple training epochs. Identified images can be reviewed and relabelled by experts, improving dataset quality and model performance. Two experiments validate the method on a fundus image dataset for referable diabetic retinopathy screening. In the first, 6% (648) of 10,788 gold-standard labels were intentionally flipped. The method identified 75.31% (488) of the flipped samples, with only 4.85% (492) false positives among correctly labelled samples. In the second, reviewing and correcting the 980 identified samples (9.1% of the dataset) and retraining the model improved best accuracy on an independent test set from 95.93% (with 6% label noise) to 96.50% (with 1.5% noise), approaching the ideal 96.57% (with 0% noise). The results demonstrate the method's effectiveness in improving model performance through automated label quality control.
Read the full abstract

All authors Zhipeng Zhang, Wenhui Shou, Wengting Ma, Dongjia Xing, Qingqing Xu, Li-Qun Xu, Qingxia Fan, Ling Xu

Computer Vision

Token-level Response-visual Attention Guidance for Multimodal LLMs Knowledge Distillation

Jaehyun Jang, Eunseop Yoon, Hee Suk Yoon et al. (+3 more)

While knowledge distillation (KD) is widely adopted for training lightweight models by leveraging supervision from larger teacher models, relying solely on output token distributions has proven insufficient for compressing Multimodal Large Language Models (MLLMs). Since output tokens are a byproduct of the model attending to visual inputs, prior works have explored explicitly distilling attention to provide a direct supervisory signal. While promising, the precise utility of which attention signals to distill remains under-explored. In this work, we challenge the conventional reliance on prompt-to-vision attention by revealing that downstream performance correlates strongly with response-to-vision attention similarity to the teacher, but negligibly with that of prompt-conditioned attention. Furthermore, we observe that attention distributions exhibit significant variance across individual tokens, indicating that a uniform distillation objective is suboptimal. To this end, we introduce Token-level Response-visual Attention Guidance (TRAG), a distillation objective that 1) shifts the focus to response-to-vision signals and 2) employs token-specific objectives by adaptively weighting the Kullback-Leibler divergence based on attention entropy, effectively guiding the student to mirror the teacher's precise visual focus. Extensive experimental results on multiple benchmarks demonstrate that TRAG significantly outperforms prior distillation baselines.
Read the full abstract

All authors Jaehyun Jang, Eunseop Yoon, Hee Suk Yoon, SooHwan Eom, Mark A. Hasegawa-Johnson, Chang D. Yoo

Computer Vision

H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation

Qixiang Yin, Huanjin Yao, Yuchen Cai et al. (+4 more)

On-policy distillation (OPD) has recently emerged as an effective post-training paradigm by providing supervision on student-generated trajectories. However, existing OPD methods for multimodal reasoning usually rely on a static teacher routing, assigning each sample to a single teacher based on modality or task type. This ignores that visual grounding and abstract reasoning may dominate different decoding steps, making a single teacher insufficient for the full trajectory. To this end, H-OPD is proposed as a confidence-aware heterogeneous multi-teacher OPD framework for multimodal reasoning. By verifying the complementarity of heterogeneous teachers in the same reasoning process, H-OPD replaces task or sample level teacher routing with token-level teacher arbitration along the shared student trajectory. H-OPD employs vision-to-language description transfer to enable text-only teachers to access key visual semantics, and uses a confidence-aware arbitration mechanism to dynamically combine vision-language teacher and text-only teachers at each token. Extensive evaluations over 11 widely-used reasoning benchmarks showcase the superior performance of our method.
Read the full abstract

All authors Qixiang Yin, Huanjin Yao, Yuchen Cai, Jianghao Chen, Ziyi Wang, Fei Su, Zhicheng Zhao

Computer Vision

CPR: Chained Perceptual Refinement for Coarse-to-Fine Medical Image Classification

Si-Yuan Lu, Hanruo Zhu, Ziquan Zhu et al. (+6 more)

High resolution medical images contain fine grained, spatially sparse cues that are critical for diagnosis, yet preserving full resolution incurs substantial computational and memory costs. Most deep models process images uniformly, leading to redundant computation or loss of diagnostic detail under downsampling. We propose Chained Perceptual Refinement, CPR, a coarse to fine framework that formulates medical image analysis as a sequential global to local decision process. Starting from a low resolution global view, CPR dynamically predicts the location and spatial extent of refinement regions, extracts high resolution evidence from the original image, and incrementally integrates it with global context. By keeping the backbone input size fixed while contracting the perceptual field, CPR preserves diagnostic fidelity with constant peak GPU memory. Extensive experiments on five medical imaging datasets and multiple backbone architectures demonstrate that CPR consistently outperforms both fixed resolution and multi scale state of the art baselines, achieving improvements of up to 2.27 percentage points over the second best method. It also achieves up to a 19.6 fold reduction in GFLOPs at matched accuracy, establishing a superior accuracy and efficiency trade off for high resolution medical image analysis. The code is available on GitHub.
Read the full abstract

All authors Si-Yuan Lu, Hanruo Zhu, Ziquan Zhu, Gaojie Jin, Zeyu Fu, Lu Yin, Ke Li, Lu Liu, Tianjin Huang