Computer Vision
Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed Tomography
Bowen Shi, Weiwei Cao, Ruifeng Yuan et al. (+5 more)
Vision-
language pre-training (VLP) holds great promise for general-purpose medical AI by leveraging radiology reports as rich textual supervision, yet existing methods struggle with 3D CT imaging due to inefficient visual backbones and coarse semantic
alignment. To address these issues, we propose a tailored VLP framework featuring three key components: (1) a CNN-ViT hybrid encoder that replaces ViT's patch
embedding with a 3D CNN backbone to efficiently capture local anatomical details while preserving global
attention and compatibility with pre-trained cross-modal priors; (2) a disease-level contrastive learning mechanism using learnable query
tokens to dynamically extract disease-specific semantics from full reports and align them with corresponding visual features, thereby disentangling distinct diseases within the same anatomical region; and (3) a diagnosis-aware
prompt strategy that employs real clinical phrases and aggregated disease prototypes to bridge the pre-training-inference gap and enhance zero-shot diagnostic reliability. Our model achieves state-of-the-art performance on CT-RATE (84.4% AUC, +5.1%) and Rad-ChestCT (75.4% AUC, +5.4%), with even larger gains (+9.8% AUC) on a challenging 60-disease
benchmark, and demonstrates strong transferability to radiology report generation, underscoring the generality and clinical utility of our approach.
Read the full abstract ▾
All authors Bowen Shi, Weiwei Cao, Ruifeng Yuan, Wanxing Chang, Wenrui Dai, Hongkai Xiong, Ling Zhang, Jianpeng Zhang
Computer Vision
TensorLDM: A Component-Wise Latent Diffusion Model for Volumetric DTI Reconstruction from Sparse DWIs
Junhyeok Lee and Kyu Sung Choi
Reconstructing
diffusion tensors from sparse DWIs is critical for accelerating
Diffusion Tensor Imaging (DTI) in clinical settings, yet current deep learning approaches frequently yield anatomically inconsistent or physically implausible tensors. We introduce TensorLDM, a component-wise latent
diffusion model that processes the six tensor components through two group-specific encoders (for diagonal and off-diagonal elements) while maintaining anatomical consistency via shared DWI conditioning. TensorLDM uses an Anatomy-Conditioned Autoencoder that encourages the latent to focus on tensor properties rather than re-encoding structural information. A shared Cross-Component
Attention (CCA) mechanism, applied in both autoencoder refinement and
diffusion fine-tuning, models inter-component dependencies, while a Mixture-of-Experts (MoE) DWI conditioner provides component-adaptive conditioning. On the Human Connectome Project (HCP)
dataset under a single-shell, four-volume sparse acquisition, TensorLDM produces the most accurate downstream tractography and tensors with near-ground-truth physical validity (SPD-violation rate 1.54% vs. 1.40%), with the best or comparable voxel-wise reconstruction accuracy. Geodesic tensor error measured by the Log-Euclidean Metric (LEM) corroborates these gains.
Read the full abstract ▾
Computer Vision
SAC$^2$-Net: Semantic Anchoring and Complementary-Consensus Fusion for Multimodal Micro-Expression Recognition
Xuepeng Zheng, Tong Chen, Chaoping Gui et al. (+3 more)
Micro-expression recognition (MER) is challenging due to subtle facial movements, limited data, and the ambiguous relationship between Action Units (AUs) and
emotion categories. Optical flow and motion magnification are two widely used representations for making subtle facial dynamics observable. However, many existing methods treat them as separate cues or fuse them without explicitly modeling their dual complementarity. Optical flow encodes displacement-level muscle motion, whereas motion magnification reveals appearance-level changes in facial texture and context. When both modalities are informative, their combination provides a more complete characterization of subtle facial dynamics; when one modality degrades, the other may still preserve discriminative evidence for compensation. This dual complementarity provides richer facial representations, but also introduces two key challenges for
multimodal fusion: cross-modal heterogeneity and spatially varying modality reliability. To address these challenges, we propose SAC$^2$-Net, a Semantic Anchoring and Complementary-Consensus Network that first aligns heterogeneous visual representations with semantic anchors and then performs reliability-aware complementary fusion. Specifically, Semantic Anchoring Soft
Alignment (SASA) converts activated AUs into textual
prompts and uses hierarchical AU-aware soft labels to align motion-magnified and optical-flow representations while preserving semantic proximity among anatomically related samples. Based on the aligned representations, Complementary-Consensus Fusion (CCF) exchanges complementary motion and appearance cues, adaptively enhances unreliable local responses with trustworthy cross-modal evidence, and further encourages a shared spatial focus through consensus refinement.
Read the full abstract ▾
All authors Xuepeng Zheng, Tong Chen, Chaoping Gui, Yingjuan Jia, Hanpu Wang, Yuhao Shan
Computer Vision
Spatio-Temporal Mixture-of-Modality-Experts Diffusion for Quantitative DCE-MRI Synthesis from Incomplete MR Sequences
Junhyeok Lee and Kyu Sung Choi
Quantitative maps from dynamic contrast-enhanced MRI (DCE-MRI) are essential for tumor assessment but are often unavailable due to contrast-
agent risks and protocol variability. Prior methods predict these maps from other MRI modalities, yet most assume fixed, fully observed inputs and fail under realistic missingness. We present Spatio-Temporal Mixture-of-Modality-Experts (ST-MoME), a conditional
diffusion framework that synthesizes 3D DCE parameter maps from diverse subsets of
multimodal MRI. ST-MoME fuses modality-specific expert features through a spatio-temporal gating network that produces voxel-wise, timestep-dependent weights, forming a conditioning tensor that guides denoising. To preserve quantitative fidelity, ST-MoME performs
diffusion directly in image space with 3D patch-based training and a Swin-based backbone. On a clinical
brain-tumor cohort of 386 patients, we evaluate ST-MoME across 16 controlled modality-availability scenarios. It achieves the lowest mean Normalized Mean Square Error (NMSE) aggregated across all three DCE parameters, with leading performance on $v_p$ and $v_e$, competitive results on $K^{\mathrm{trans}}$, and the lowest reconstruction error within the clinically critical tumor region. A post-hoc analysis of the learned gating dynamics shows a structural-early, physiological-late fusion schedule consistent with clinical intuition.
Read the full abstract ▾
Computer Vision
PatchINR: Patch-Based Implicit Neural Representations for Efficient and Scalable Inference
Jiachen Ren, Wenyong Zhou, Taiqiang Wu et al. (+4 more)
Implicit Neural Representation (INR) provides an effective approach for continuous signal modeling, but classical per-pixel inference results in quadratic growth in inference count, leading to dramatically increased computational costs in high-resolution application scenarios. To address this issue, we propose a patch-based approach that treats non-overlapping patches as fundamental processing units and predicts entire pixel patches in a single forward pass, significantly reducing the number of inference queries required. To validate the effectiveness of our approach, we propose a hardware acceleration architecture on the Field Programmable Gate Array (FPGA) platform for the INR model, which features a configurable pipeline and supports dual-precision computation. Our patch-based INR achieves comparable reconstruction quality to pixel-level INR (34.97 dB PSNR with 2 x 2 patches) while reducing inference latency by 75% with only 0.6% parameter overhead.
Read the full abstract ▾
All authors Jiachen Ren, Wenyong Zhou, Taiqiang Wu, Yuxin Cheng, Xincheng Feng, Zhengwu Liu, Ngai Wong
Computer Vision · Cross-listed from cs.RO
ASSCG: Just-Right Gating over Chattering for Fast-Slow LLM Planning in Autonomous Driving
Sining Ang, Yuan Chen, Liu Haiyan et al. (+5 more)
Large
language models (LLMs) can improve autonomous driving planning but are costly to query online, and existing fast-slow planners often rely on hand-designed triggering rules that either over-call the slow system or call it at the wrong times. We formulate slow-system invocation as a resource-aware sequential decision problem and propose the Adaptive Slow-System Control Gate (ASSCG), which makes frame-level Query/Cache/Drop decisions to refresh, reuse, or suppress slow guidance. ASSCG uses an RWKV backbone for efficient long-horizon gating and is trained with supervised fine-tuning followed by GRPO-style compute-aware reinforcement fine-tuning. We apply ASSCG to two different fast-slow architectures: (i) AsyncDriver on nuPlan Hard20 closed-loop evaluation, where ASSCG improves score to 67.28 (+2.28) while reducing average end-to-end inference latency by 60%; and (ii) a RecogDrive-based dual system that we build by replacing its original VLM-2B module with a lightweight ViT-based fast planner and adding an LLM slow planner, evaluated on NAVSIM, where ASSCG achieves 91.4 PDMS (+0.6) and increases average speed by 25%. The project page, including
video visualizations and additional results, is available at https://williamxuanyu.github.io/asscg/.
Read the full abstract ▾
All authors Sining Ang, Yuan Chen, Liu Haiyan, Xuanyao Mao, Jason Bao, Xuliang, Bingchuan Sun, Yan Wang
Computer Vision
C2RM-Seg: Causal Counterfactual Reasoning with Structural-Semantic Priors for Weakly Supervised Histopathological Tissue Segmentation
Hualong Zhang, Siyang Feng, Zihan Huan et al. (+4 more)
Histopathological tissue
segmentation is essential for computer-aided diagnosis, yet weakly supervised methods often suffer from noisy pseudo-labels generated by Class Activation Mapping (CAM). Existing CAM approaches tend to focus on staining-driven appearance cues rather than true causal tissue morphology, resulting in spurious localization and poor structural consistency. To address this issue, we propose C$^2$RM-Seg, a two-stage framework that integrates causal pseudo-label refinement with structure-aware semantic enhancement. For classification, we introduce a Causal Counterfactual
Reasoning Module (C$^2$RM) that decomposes features into latent factors and performs counterfactual intervention via a learned causal structure
matrix, suppressing confounding context and producing morphology-aligned CAMs. For
segmentation, we design a Dual-Path Structural-Semantic Architecture that combines fine-grained structural features from ResNeSt with global semantic priors from a frozen DINOV3 foundation model. A cross-path gating mechanism adaptively regulates semantic injection using local structural cues to preserve boundary fidelity. To further mitigate residual pseudo-label noise, we propose an Uncertainty-Gated Margin (UGM) loss, which dynamically balances margin enforcement and confidence learning based on prediction uncertainty. Extensive experiments on two public histopathological tissue
datasets show that C$^2$RM-Seg achieves state-of-the-art performance.
Read the full abstract ▾
All authors Hualong Zhang, Siyang Feng, Zihan Huan, Yi Qian, Zhenbing Liu, Rushi Lan, Xipeng Pan
Computer Vision · Cross-listed from cs.RO
AISPO: Enhancing Depth Reliability for Robotic Manipulation of Non-Lambertian Objects via Affine-Invariant Shape Prior
Zhiming Chen, Linfang Zheng, Kun Zhang et al. (+4 more)
Reliable depth perception is critical for robotic manipulation, especially for non-Lambertian objects such as transparent or highly specular surfaces, where raw depth measurements are often corrupted or missing. These failures frequently propagate to motion planning, resulting in invalid grasp poses and execution errors. We propose AISPO, a depth completion framework that improves depth reliability for manipulation in challenging sensing conditions. AISPO combines multi-scale RGB-D feature fusion with an affine-invariant shape prior to enforce
geometric consistency and mitigate catastrophic depth failures. Unlike methods that focus primarily on average depth accuracy, our approach emphasizes physical plausibility and structural integrity of the predicted depth maps. Extensive
benchmark evaluations demonstrate competitive performance and strong generalization to unseen objects and novel scenes. Real-world grasping experiments further show that enhanced depth reliability significantly improves manipulation success rates, particularly for transparent objects where many existing methods fail to produce physically usable depth estimates.
Read the full abstract ▾
All authors Zhiming Chen, Linfang Zheng, Kun Zhang, Hyung Jin Chang, Wei Zhang, Hongyu Yu, Hua Chen
Computer Vision
HG-Bench: A Benchmark for Multi-Page Handwritten Answer-Region Grounding in Automated Homework Assessment
Chuangxin Zhao, Boyan Shi, Yanling Wang et al. (+7 more)
Automated homework assessment depends not only on recognizing student answers, but also on accurately locating where each answer and each intermediate
reasoning step appears in noisy, multi-page handwritten work. This paper addresses the missing evaluation setting of page-aware, two-level answer-region grounding: given a sequence of homework page images, a model must localize complete answer regions and their ordered step-level subregions. We introduce HG-Bench, a
benchmark of 500 human-annotated K-12 homework samples curated from a 1,489,278-image source pool, with question-level and step-level boxes linked by a hierarchical containment constraint. HG-Bench is paired with a page-aware evaluation protocol that separately measures complete-answer localization (FA) and step-level decomposition (FSm), revealing whether models truly ground the spatial structure of student
reasoning rather than merely parse visible text. Across frontier closed-source APIs and competitive open-weight VLMs, no zero-shot system exceeds 55.22% on FA or 48.22% on FSm, while a GLM-4.6V 9B reference model fine-tuned on ~10k in-domain examples reaches 74.97/72.26. These results identify step-level handwritten grounding as a concrete capability gap and provide a reproducible
benchmark, evaluation protocol, and trained reference point for future work on automated homework assessment.
Read the full abstract ▾
All authors Chuangxin Zhao, Boyan Shi, Yanling Wang, Yijian LU, Canran Xiao, Jiali Chen, Jun Xia, Yan Wang, Ji Qi, Juanzi Li
Computer Vision
Independent Samples, Correlated Variance A Learnable Cross-View Cue in Path-Traced Stereo Data
Po-Ting Lin
Path-traced synthetic stereo is a primary training substrate for disparity networks, and the pipelines that consume it assume Monte~Carlo (MC) rendering noise is independent across the two views. The assumption is correct at the level it is stated—individual samples—but silent about the object a network actually sees. We show that the per-pixel MC variance fields, though built from independent samples, are strongly correlated once aligned by the ground-truth disparity, and that a network can learn to match with that correlation. Across 20 indoor scenes the warped correlation is $0.754\pm0.016$ against $0.360$ unwarped; it replicates on a second renderer with a different sampler and sample budget ($0.743\pm0.044$), and a seed-count analysis puts the population value near $0.85$, making the measurement a lower bound. The effect is field-level, not sample-level: at the warp correspondence the signed per-seed residual correlation is $-0.0004$ while the residual envelope correlates at $0.38$. A capacity-limited siamese probe given nothing but variance-field patches reaches $78.8\%$ two-alternative forced-choice accuracy on held-out scenes and falls to chance once the
alignment is destroyed; under the ordinary single-render condition, decorrelation still costs $2.40$ percentage points in a difference-in-differences design, positive in all six held-out scenes. A real sensor's variance is fixed by its own signal rather than by transport difficulty, so across views it is redundant with intensity: the cue is specific to rendered data.
Read the full abstract ▾
Computer Vision
TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition
Minghao Zhu, Xiao Lin, Mengxian Hu et al. (+5 more)
Adapting CLIP for open-vocabulary
video recognition necessitates a delicate balance between newly acquired
video knowledge and the pretrained generalization. While existing studies pursue this generalization-specialization trade-off with additional regularizations or constraints, we argue that they overlook the deviation of representations beyond the fine-tuning data distribution, resulting in suboptimal adaptation effects. We believe such deviation is inherited from the inconsistency between the fine-tuning and evaluation objectives, where model optimization is restricted to the known training distribution but evaluated on unseen ones. In this paper, we introduce TACO, a simple yet effective framework to mitigate the potential negative effects induced by this inconsistency. Our key insight is that adaptation should preserve OOD-relevant
alignment beyond the training distribution. To this end, we propose Relative Structure
Distillation, which regularizes the relative geometry of the representation space and suppresses harmful
alignment shift during training. We further decouple the representation space from the optimization space with a lightweight specialization projection, allowing task-specific adaptation without directly overspecializing the representations used at test time. TACO establishes state-of-the-art performance on diverse
benchmarks under cross-
dataset and base-to-novel settings. Code will be released at https://github.com/ZMHH-H/TACO.
Read the full abstract ▾
All authors Minghao Zhu, Xiao Lin, Mengxian Hu, Xun Zhou, Liuyi Wang, Xiaoyan Qi, Chengju Liu, Qijun Chen
Computer Vision
Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models
Kaiwen Zheng, Guande He, Min Zhao et al. (+7 more)
Autoregressive
video diffusion with causal
diffusion transformers has emerged as a major paradigm for real-time streaming
video generation and action-conditioned interactive world models. In this work, we extend rCM, an advanced
diffusion distillation framework, to autoregressive
video diffusion. The core philosophy of rCM lies in the complementarity between forward and reverse divergences, represented by consistency models (CMs) and distribution matching
distillation (DMD), respectively, in
diffusion distillation. This philosophy naturally carries over to the autoregressive setting, where teacher-forcing (TF) provides an offline, forward-divergence causal training paradigm, while self-forcing (SF) corresponds to an on-policy, reverse-divergence refinement. Our contributions are: (1) through extensive experiments, we show that teacher-forcing CM is currently the best complement to self-forcing DMD as an initialization strategy (2) we present the first implementation of teacher-forcing-based continuous-time CMs (e.g., sCM/MeanFlow) for autoregressive
video diffusion, enabled by our custom-mask FlashAttention-2 JVP kernel, achieving 10$\times$ faster convergence compared to discrete-time CMs (dCMs) (3) we introduce Causal-rCM, a leading, unified, and scalable
algorithm-infrastructure open recipe for
diffusion distillation and causal training (4) we achieve state-of-the-art streaming
video generation performance in both frame-wise and chunk-wise settings, using only synthetic data for training. Notably, our distilled 2-step causal Wan2.1-1.3B model achieves a VBench-T2V score of 84.63 with only 1 or 2 sampling steps. We further apply Causal-rCM to Cosmos 3, an advanced omnimodal world foundation model for physical AI with action-conditioned generation capability, enabling an interactive world model.
Read the full abstract ▾
All authors Kaiwen Zheng, Guande He, Min Zhao, Jintao Zhang, Huayu Chen, Jianfei Chen, Chen-Hsuan Lin, Ming-Yu Liu, Jun Zhu, Qianli Ma
Computer Vision
EchoStyle: Unlocking High-Fidelity Video Stylization with Reverse Data Synthesis
Huaqiu Li, Jiahao Wang, Sijia Cai et al. (+4 more)
While image stylization has been studied extensively,
video stylization remains a critical and largely unsolved challenge in the field of intelligent content creation. Existing methods, usually utilizing a reference image as the style prior, suffer from content leakage, data scarcity and limited adaptability to long
videos, leading to suboptimal results with severe style drift and motion distortion. For these issues, we present EchoStyle, a scalable text-driven framework to achieve high-quality stylization of
videos with arbitrary lengths. To start with, we construct a
video-to-
video architecture to appropriately re-fuse the
video content and the text style. To address data scarcity, we pioneer an automatic reverse-synthesis pipeline to establish V-Style20k, a large-scale stylization
dataset of 20k high-quality
video pairs. To facilitate long
video stylization, we devise an init-follow-mode mechanism along with a sliding-window inference strategy. Extensive experiments demonstrate EchoStyle's excellent performance across a wide range of artistic styles, even comparable to leading closed-source solutions.
Read the full abstract ▾
All authors Huaqiu Li, Jiahao Wang, Sijia Cai, Hualian Sheng, Bing Deng, Jieping Ye, Wenhan Luo
Computer Vision
C3-Bench: A Context-Aware Change Captioning Benchmark
Jae-Woo Kim, Hyeongbeom Kim and Ue-Hwan Kim
While Change Captioning systems have garnered substantial
attention to respond to our evolving world, their true performance on diverse real-world change contexts remains largely unexplored due to the lack of comprehensive evaluation frameworks. To fill this gap, we propose C3-Bench, a comprehensive
benchmark for evaluating Context-aware Change Captioning. C3-Bench features: (1) 4,996 human-labeled image pairs of 51 real-world change contexts across four domains (e.g., natural scenes, remote sensing imagery, image editing, and anomalies), each with diverse, carefully curated scenarios derived from multiple change-centric communities; and (2) the first LLM-as-Judge evaluation framework in the change captioning task that measure fine-grained dimensions (e.g., correctness, specificity, fluency, and relevance), along with a novel reversibility metric exploring whether models understand changes with symmetric consistency. Based on C3-Bench, we
benchmark 32 models – including conventional change captioning models, proprietary Large
Multimodal Models (LMMs), and 2B-90B open-source LMMs. We reveal a fundamental blind spot in the prevailing change captioning paradigm: Once the change context departs from training-style regimes, conventional models collapse, and even state-of-the-art LMMs such as GPT-5.2 exhibit systematic domain- and position-dependent errors that distort reliable change understanding. By making these hidden failure modes explicit and measurable, we delineate the next frontier for building generalizable and trustworthy change captioning systems. All codes and
datasets are publicly available on the project page.
Read the full abstract ▾
Computer Vision
LinStereo: Linear-Complexity Global Attention for Multi-Scale Iterative Stereo Matching
Yiran Wang, Oliver Turner and Viorela Ila
Existing
Vision Foundation Model (VFM)-based iterative stereo pipelines under-exploit three information pathways: multi-scale backbone features are collapsed into single-level correlations,
geometric priors remain untapped at initialization, and context propagates only locally. These gaps widen under degraded photometric cues, making
underwater scenes a stringent generalization test. To address this, we propose LinStereo, built upon Depth Anything V3, whose core is a Position-Aware Linear
Attention (PALA) module that replaces local recurrence with global aggregation at linear cost, propagating reliable estimates from well-matched regions into degraded areas while preserving disparity structure. PALA is made effective by two enabling components: Hierarchical Semantic Cost Volumes (HSCV), which supply scale-aligned correlations from the VFM feature hierarchy, and a Depth Prior Initialization (DPI) that converts
monocular depth into a metrically calibrated warm start. LinStereo achieves state-of-the-art-level accuracy on standard
benchmarks and strong cross-domain generalization, particularly on
underwater scene where severe photometric degradation makes stereo matching particularly challenging, attaining the best overall accuracy with consistent gains 28% lower AbsRel on TartanAir-UW, 26% on SQUID, a real-world
underwater dataset).
Read the full abstract ▾
Computer Vision · Cross-listed from cs.LG
Brevity is the Soul of Inference Efficiency: Inducing Concision in VLMs via Data Curation
DatologyAI: Matthew L. Leavitt, Siddharth Joshi, Haoli Yin et al. (+6 more)
Inference efficiency is typically pursued by shrinking the model:
distillation,
pruning, quantization, and sparse routing each lower per-
token cost while treating
token count as fixed. But output length has been inflating, and it is precisely the component the standard toolkit leaves untouched. Here, we argue that brevity is the missing inference-efficiency lever, and that pretraining data curation is a practical way to pull it: a model trained on concise, correct data learns to answer in fewer
tokens; i.e. it has a lower Cost-of-Pass. We apply our VLM curation pipeline to the MAmmoTH-VL single-image subset, and compare models trained on our curated data, the standard MAmmoTH-VL data, and external open-weight frontier VLMs. On a controlled 20-evaluation set and 14 VLMs at 1B-4B activated parameters, we hold output length fixed with a per-model regression, separating brevity from quality, and price models in FLOPs per correct answer. Curation buys a 35x Cost-of-Pass advantage over the most verbose 4B comparator (Qwen3.5-4B) within $\sim$1 pp of accuracy (0.41 vs 14.58 TFLOPs per correct answer; 0.691 vs 0.704 mean accuracy). Curation also buys a +17.55-percentage-point matched-length accuracy gain over the uncurated baseline that grows with model scale (from +16.7 pp at 1B to +21.2 pp at 4B). This brevity improvement concedes no quality: generic verbosity buys no accuracy at any capability or scale, and the window where
reasoning-structured verbosity still earns its
tokens shrinks from 4 of 8 capability groups at 2B to 1 of 8 at 4B. Per example, the concise model even reaches correct answers the verbose
reasoning model misses, marking
reasoning as a distinct curation target rather than something brevity gives up. Inference efficiency in this regime is a
tokens-per-correct problem, and brevity is the lever that targets it directly.
Read the full abstract ▾
All authors DatologyAI: Matthew L. Leavitt, Siddharth Joshi, Haoli Yin, Rishabh Adiga, Haakon Mongstad, Alvin Deng, David Schwab, Bogdan Gaza, Ari Morcos
Computer Vision
PRISM: Feed-Forward Single-Image 3D Reconstruction via Geometric Warp-Residual Modeling
Zhijie Zheng, Xinhao Xiang and Jiawei Zhang
Reconstructing 3D scenes from a single image is a fundamental challenge in computer
vision, with broad applications in virtual reality, robotics, and content creation. Recent methods achieve outstanding performance by leveraging camera-controlled
video diffusion models, but rely on iterative
diffusion sampling, which greatly limits their practical deployment. We observe that
geometric forward warping alone can cover the majority of a target view directly from the input image, with only a compact residual left for the encoder to correct. Motivated by this observation, we propose PRISM, a feed-forward framework that decomposes multi-view latent prediction into a parameter-free
geometric prior and a learned residual correction, with no
diffusion sampling required at inference. To enable generalization from purely synthetic training data, we devise a two-stage training strategy combining latents supervised
distillation for
geometric generalization and perceptual fine-tuning for appearance quality optimization. Extensive experiments on three
benchmarks demonstrate that PRISM achieves competitive reconstruction quality compared with
diffusion-based methods, while reducing inference time dramatically to only 36 seconds per scene. Our code is available at https://github.com/microjie372/PRISM.
Read the full abstract ▾
Computer Vision
Gastroendoscopy View Synthesis: A New Real Dataset and Evaluation
Masaki Minai, Yusuke Monno, Masatoshi Okutomi et al. (+1 more)
Novel view synthesis (NVS) is an active research topic in computer
vision, owing to the success of neural radiance field (NeRF) and 3D Gaussian splatting (3DGS) methods. While NVS opens the door to potential applications in gastroendoscopy, such as extending the field of view of endoscopic images and enabling digital twins for 3D archiving and endoscopist manipulation training, the
dataset is insufficient to evaluate NVS for gastroendoscopy. In this paper, we present the first real gastroscopy
dataset for NVS, namely the GastroNVS
dataset, which contains a set of gastroscopic images, camera poses, and a point cloud for real gastroendoscopy inspection. To assess the suitability of the GastroNVS
dataset, we evaluate several 3DGS methods and discuss the challenges for future development. The
dataset is available on request from our project page.
Read the full abstract ▾
All authors Masaki Minai, Yusuke Monno, Masatoshi Okutomi, Sho Suzuki
Computer Vision
Teach-to-Reason: Competition-Guided Reasoning with a Self-Improving Teacher
Xiao Han, Hao Liu, Zhimin Bao et al. (+5 more)
Chest X-ray visual question answering (CXR VQA) requires models not only to predict correct answers, but also to produce reliable medical
reasoning. However, existing reinforcement-learning-based training typically relies on answer-level rewards, which are often too coarse to improve chain-of-thought (CoT) quality and can become ineffective when group-level advantages collapse to zero. We propose Teach-to-Reason (T2R), a framework that introduces comparison-based supervision into CoT optimization through a self-improving Teacher and a competition-guided Reasoner. As the Teacher is iteratively strengthened via self-competition, the Reasoner is optimized against progressively stronger Teacher-generated references. We further introduce a case-wise reward design that preserves the original reward-induced positive/negative partition when it is informative, and restores supervision from competition scores when the original reward signal degenerates. Experiments on multiple CXR open-ended VQA
benchmarks show that T2R consistently outperforms strong baselines, indicating that comparison-based supervision, when integrated in a controlled and principled manner, provides a more effective training signal for
reasoning optimization.
Read the full abstract ▾
All authors Xiao Han, Hao Liu, Zhimin Bao, Jile Jiao, Yue Wang, Hui Guo, Xiaofeng Mou, Yi Xu
Computer Vision
Anatomically-conditioned Latent Diffusion Model for Data-Efficient Few-Shot Cross-Domain 3D Glioma MRI Synthesis
Salman Shaik, Truong Thanh Hung Nguyen and Hung Cao
Accurate classification of diffuse gliomas is often hindered by domain shifts across centers and a lack of large, annotated
datasets. We propose the Anatomically-conditioned Latent
Diffusion Model (ALDM), a novel framework for data-efficient, few-shot 3D volumetric MRI synthesis. ALDM utilizes a two-stage approach: a 3D variational autoencoder learns anatomical priors from a data-rich source domain, while a conditional latent
diffusion model, guided by tumor masks via a ControlNet, generates structurally coherent volumes for a data-scarce target domain. Evaluated in an extreme few-shot setting with only 16 target images, ALDM outperformed GAN and hybrid baselines, achieving a superior Frechet Inception Distance (FID) of 85.40 and a downstream classification AUC of 0.987. Qualitative results confirm that the model preserves sharp pathology boundaries and cross-modal consistency, with visual fidelity improving progressively during training. By capturing essential diagnostic features, ALDM provides a robust tool for clinical data augmentation in low-resource settings. Our implementation is available at https://github.com/Analytics-Everywhere-Lab/anatomically-conditioned-LDM.
Read the full abstract ▾
Computer Vision
Transferable Attack against Face Swapping in an Extended Space
Mingzhi Lyu, Yi Huang, Jun Xie et al. (+3 more)
Although deep Face Swapping (FS) models may benefit the entertainment industry, they pose severe threats to
privacy and security. Existing protections, including deepfake detection and
adversarial perturbation, are either passive responses or ineffective to unseen subject-agnostic FS models. In this paper, we propose a transferable attack against subject-agnostic FS models named Additive Identity attack based on a Relighting function (AIR). AIR leverages reillumination and additive perturbations to mislead the identity extraction modules in subject-agnostic FS models. By using these two types of perturbations simultaneously, the attack space is extended such that stronger but more visually natural
adversarial examples can be identified. To further enhance the visual quality while preserving the effectiveness of the attack, an adaptive translation-invariant operation and an illumination control scheme are designed for AIR. Unlike other methods, AIR does not require a surrogate FS model to achieve high transferability. In addition, a mathematical proof is given for the extension of the attack space. Extensive experiments using 1000 image pairs across various state-of-the-art subject-agnostic FS models, including GAN and
diffusion-based FS models, show that AIR surpasses all existing attacks in terms of both attack success rate and image quality.
Read the full abstract ▾
All authors Mingzhi Lyu, Yi Huang, Jun Xie, Zihao Zhao, Hong Xu, Adams Wai-Kin Kong
Computer Vision
Text Over Image: Auditing Multimodal Robustness in Synthetic Medical Image Detection
Ching-Hao Chiu, Hao-Wei Chung, Gelei Xu et al. (+7 more)
With the rapid adoption of generative AI, synthetic medical images pose growing risks, including diagnostic deception and insurance fraud. Although prior work has explored
vision-
language model (VLM)-based synthetic image detection, these evaluations typically consider images in isolation. In clinical practice, however, images are interpreted alongside structured records and metadata, and VLMs are increasingly deployed under joint image-record inputs. We uncover a previously underexamined
multimodal vulnerability: when given both modalities, VLMs may overweight record context in authenticity judgments, such that the same image receives different predictions solely due to changes in its accompanying text. This raises concerns about robustness in real-world deployment. To systematically characterize this effect, we reformulate synthetic medical image detection as an audit of
multimodal robustness at the image-record interface and introduce a paired
benchmark that holds the image fixed while swapping controlled metadata variants. Across multiple imaging modalities, we evaluate diverse open-weight and frontier API VLMs and find that changing the metadata context alone can flip authenticity judgments, with accuracy on authentic images dropping by 61.1% on average under an explicit AI-origin tag. We further propose an inference-time mitigation pipeline that detects and neutralizes provenance shortcuts without model retraining, substantially outperforming direct
prompt-based suppression on the affected subset. Our
benchmark provides a standardized tool for assessing and improving
multimodal robustness beyond image-only settings. Code and data will be released upon acceptance.
Read the full abstract ▾
All authors Ching-Hao Chiu, Hao-Wei Chung, Gelei Xu, Xueyang Li, Pin-Yu Chen, John Kheir, Meysam Ghaffari, Carlos Morato, Ahmed Abbasi, Yiyu Shi
Computer Vision
Hypergraph Normal World Models for Logical Visual Anomaly Detection
Weizhi Nie, Zibo Xu, Weijie Wang et al. (+1 more)
Visual anomaly detection is often deployed with only normal training images. Most one-class detectors map test patches or features to a normal reference distribution. This works well for local structural defects. Logical anomalies are different. Each visible part may look normal, while the whole image violates a normal count, co-occurrence, or spatial relation. This paper studies whether a model can learn such a category-specific normal world from nominal images alone. We propose the Hypergraph Normal World Model, a normal-only detector that distills frozen DINOv2 patch
tokens into patch, relation, and hypergraph statistics. It builds spatial hyperedges over
token groups. It then scores each test image with an information quotient that separates local, relational, hyperedge, and hyperedge-relation evidence. On the available MVTec LOCO breakfast-box validation data, the full hypergraph model improves logical anomaly AUROC from 0.8434 for DINOv2 patch-kNN to 0.9279. It also improves over the non-hypergraph variant, from 0.9013 to 0.9279. Few-shot experiments show that the model remains effective with very limited normal images. We also test whether the score reflects normal-world knowledge rather than a shallow mapping. t-SNE separates logical anomalies in the learned energy space. Relation counterfactuals increase the information quotient by 83.13 on average. Random hypergraphs reduce logical AUROC, and hyperedge attribution is much larger on logical anomalies. Qualitative examples show that high scores are driven by relation-bearing terms. These results suggest that logical visual anomaly detection should model normal relations, not only normal local patches.
Read the full abstract ▾
All authors Weizhi Nie, Zibo Xu, Weijie Wang, Yuting Su
Computer Vision · Cross-listed from cs.LG
Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning
Hongye Xu and Bartosz Krawczyk
Exemplar-free class-incremental learning (EFCIL) requires stable decision boundaries within a shifting feature space. While maintaining class-conditional Gaussian statistics provides a principled classification strategy, these parametric summaries remain sensitive to anisotropic representation drift. Existing methods often transport these statistics across tasks using a decoupled, post-hoc paradigm: optimizing a backbone without explicit
geometric constraints can distort the legacy
manifold, limiting the precision of retroactive
alignment. In this paper, we formulate feature transport as an endogenous training constraint rather than a separate post-task step, presenting the Geometry-Anchored Transport Framework. First, we derive an Analytic
Geometric Anchor via Mahalanobis-aligned regression to mitigate macroscopic anisotropic drift. Second, we introduce a
Topology-Aware
Evolution objective that regularizes localized
manifold degradation while calibrating a residual network against the analytic prior. By coupling
manifold evolution with transport constraints during the primary training phase, our framework mitigates evaluation errors without requiring decoupled fine-tuning. Experiments across CIFAR-100, TinyImageNet, and ImageNet-100 demonstrate that the proposed framework consistently improves upon existing post-hoc alternatives under strict exemplar-free constraints.
Read the full abstract ▾
Computer Vision
Follow Your Track: Precise Skeleton Animation Controlled by 3D Trajectories
Yueting Liu, Yanqin Jiang, Nian Liu et al. (+4 more)
4D generation aims to animate 3D objects with realistic motion, holding great promise for applications. Existing methods typically decouple 3D asset generation from motion synthesis: acquire a 3D asset, prepare a structural representation like mesh and Gaussians, and synthesize motion from text or
video control signals. However, dense mesh and Gaussian representations incur high computational costs and are prone to temporal artifacts, limiting animation quality and duration to only short clips. Meanwhile, text lacks fine-grained spatial and temporal details such as timing and coordination, while
video entangles motion with appearance and background. Together, these limitations result in 4D animations that suffer from poor temporal consistency, wrong identification, and limited controllability. We address these issues with ACT, a trajectory-conditioned framework for
topology-general skeletal animation. ACT uses skeletons as a compact structured and compute-efficient representation and 3D point trajectories from
monocular video as explicit motion guidance which provide detailed motion patterns without appearance
entanglement. At the core of ACT is a Routed Trajectory Injector, which achieves accurate and robust trajectory-to-joint transfer through three complementary designs: prior-guided hard routing establishes precise skeleton-to-mesh correspondences, global routing enables holistic joint-track interaction for full-body motion awareness, and local windowed cross-
attention enforces fine-grained temporal
alignment, improving micro-timing and reducing motion misalignment across varying motion rates. Extensive experiments demonstrate that ACT significantly outperforms existing methods in fidelity and temporal consistency.
Read the full abstract ▾
All authors Yueting Liu, Yanqin Jiang, Nian Liu, Jingmen Zhou, Zhengjun Zha, Weiming Hu, Jin Gao
Computer Vision
Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity
Heethanjan Kanagalingam, Thenukan Pathmanathan, Mokeeshan Vathanakumar et al. (+3 more)
Vision Language Models have achieved near-human performance on single-document Visual Question Answering, yet their effectiveness degrades significantly when retrieving information from large collections of visually homogeneous documents. Existing multi-document
benchmarks aggregate diverse document types, creating artificial separation in
embedding space that does not reflect enterprise document repositories where thousands of records share identical visual templates. We identify this as
embedding collapse and introduce Invoice Haystack, a
benchmark with 1,500 anonymized invoice images paired with 200 discriminative question-answer pairs, specifically designed to stress-test
retrieval under strong visual homogeneity. Invoice Haystack exhibits a mean pairwise cosine similarity of 0.73, compared to 0.38 (DocHaystack) and 0.31 (InfoHaystack) in existing
benchmarks, posing a fundamentally more challenging
retrieval problem. Addressing the identified challenge, we propose VL-RAG, a hybrid
retrieval-augmented generation framework that jointly leverages text and visual
embeddings to harness the complementary strengths of both modalities, followed by a VLM-based verification filter for precise document identification. VL-RAG achieves 60.0% Recall@1 on Invoice Haystack-500, outperforming existing state-of-the-art method by up to an absolute 13.5 percentage points. It further improves
retrieval considerably on DocHaystack-1000 (77.1% vs.\ 75.2%) and InfoHaystack-1000 (84.5% vs.\ 80.0%), establishing the proposed dual-stream fusion as a consistently superior
retrieval strategy across both homogeneous and heterogeneous document collections.
Read the full abstract ▾
All authors Heethanjan Kanagalingam, Thenukan Pathmanathan, Mokeeshan Vathanakumar, Basim Azam, Sarah Monazam Erfani, Naveed Akhtar
Computer Vision
State Space Models Meet Remote Sensing: A Survey
Qinzhe Yang, Chenyang Liu, Jia Xu et al. (+2 more)
State Space Models (SSMs), designed for long-range modeling, offer linear computational complexity and strong capabilities in capturing long-range dependencies. In the field of remote sensing, SSMs have gained popularity due to their effectiveness in addressing unique challenges such as dense visual predictions, multi-modal remote sensing data, and temporal remote sensing data, which have also yielded significant advancements in customized architectures. This paper presents a comprehensive review of SSM-based approaches in remote sensing, covering most of the relevant studies since SSMs were first introduced to the field. We offer a multi-dimensional analysis examining SSM applications in remote sensing tasks and discussing advancements in architecture design. This paper not only synthesizes the rapid progress in SSM-based research but also identifies key challenges and future opportunities. By providing a detailed perspective, this paper aims to serve as a foundational resource for remote sensing researchers, offering actionable insights to foster further advancements in this evolving domain. We will keep tracing related works at https://github.com/QinzheYang/Awesome-RS-State-Space-Model.
Read the full abstract ▾
All authors Qinzhe Yang, Chenyang Liu, Jia Xu, Zhenwei Shi, Zhengxia Zou
Computer Vision
Efficient Remote Sensing Instance Segmentation with Linear-Time State Space Distilled Visual Foundation Models
Qinzhe Yang, Keyan Chen, Jia Xu et al. (+2 more)
The computational complexity of
Transformers scales quadratically with the number of
tokens, which significantly constrains the efficiency of
vision models, particularly recent ViT-based foundation models in dense prediction tasks. Instance
segmentation, a typical dense visual prediction task in the remote sensing field, faces similar challenges. In this paper, inspired by the recent advances of knowledge
distillation in large
language models, we introduce RS4D - a new remote sensing instance
segmentation method with linear computational complexity, which addresses the inefficiency of long sequence modeling through distilled state space modeling (SSM). We propose an adaptive noise and masking knowledge
distillation training method for pre-training lightweight SSM backbones, which effectively compresses knowledge from the vast self-
attention space into a compact, dense linear state space. We also design a remote sensing image instance
segmentation architecture based on this lightweight visual encoder, where we explore variants of three different backbones and two
segmentation heads. Extensive experiments are conducted on multiple
benchmark datasets, including SSDD, WHU, and NWPU. Compared to ViT-based approaches, our proposed SSM backbone achieves an 8x reduction in parameters and a 9x reduction in FLOPs while maintaining comparable or superior accuracy to both ViT- and CNN-based instance
segmentation methods. The implementation codes have been publicly available at https://github.com/QinzheYang/RS4D.
Read the full abstract ▾
All authors Qinzhe Yang, Keyan Chen, Jia Xu, Zhenwei Shi, Zhengxia Zou
Computer Vision
V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning
Haoxiang Sun, Zhihang Yi, Langxuan Deng et al. (+6 more)
Fine-grained visual
reasoning requires
multimodal large
language models (MLLMs) to identify task-relevant visual evidence and ground their
reasoning in local image regions. Existing agentic methods typically rely on reinforcement learning with verifiable rewards or supervised fine-tuning on large-scale annotated
reasoning traces, leading to costly exploration, hand-designed verification rules, or heavy dependence on textual supervision. A natural way to avoid such external answer labels is to learn from trajectories sampled by the student itself, which points to On-Policy
Distillation (OPD). To understand what OPD can and cannot provide for visual
reasoning, we revisit it as negative-free stop-gradient
alignment. This perspective shows that, although OPD provides effective
token-level correction, its ceiling is constrained by the absence of trajectory-level discrimination. Motivated by these observations, we propose V-Zero, an answer-label-free framework for visual
reasoning with contrastive evidence gating. V-Zero uses no annotated textual answer labels; instead, during training it pairs a question-relevant regional crop with a negative visual view to evaluate student-sampled trajectories and gate dense
token-level
distillation. Experiments on multiple visual
reasoning benchmarks show that V-Zero consistently improves fine-grained visual
reasoning while preserving strong generalization. Notably, V-Zero is more than 5$\times$ faster than previous supervised fine-tuning methods and more than 10$\times$ faster than reinforcement learning baselines. Code and
dataset will be released at https://github.com/eVI-group-SCU/V-Zero
Read the full abstract ▾
All authors Haoxiang Sun, Zhihang Yi, Langxuan Deng, Yuhao Zhou, Peiqi Jia, Jian Zhao, Li Yuan, Jiancheng Lv, Tao Wang
Computer Vision
REViT: Roto-reflection Equivariant Convolutional Vision Transformer
Sheir A. Zaheer, Alexander C. Holston and Chan Y. Park
In this paper, we propose a discrete roto-reflection group equivariant
vision transformer with convolutional
attention. Roto-reflection equivariant networks preserve the rotational, flip and positional
symmetry in feature maps, making them useful for tasks where orientation of the inputs is relevant to the model outputs. In image classification and object detection, most of the studies on roto-reflection equivariant models have focused on using convolutional neural networks rather than
vision transformers. In this paper, we examine the challenges involved in achieving equivariance in
vision transformers, and we propose a simpler way to implement a discretized roto-reflection group equivariant
vision transformer. The experimental results demonstrate that our approach outperforms the existing approaches for developing discrete roto-reflection group equivariant neural networks for image classification.
Read the full abstract ▾