Peer Revenue Publish or profit

Papers

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

Computer Science Computer Vision

cs.CV Watch Computer Vision

Thursday 4 June

Computer Vision

Comparison of Deep Learning Frameworks For Rice Disease Mapping From UAV Multispectral Imaging

Yadav Raj Ghimire, Jagrati Talreja, Tewodros Syum Gebre et al. (+3 more)

In this study, UAV multispectral imagery is used to segment the severity of bacterial leaf blight (BLB) in rice using convolutional neural networks (CNNs) and transformer-based models. The evaluated architectures include U-Net with a ResNet- 101 encoder, U-Net++ with EfficientNet-B3 and EfficientNetB7, DeepLabV3+, and SegFormer, all trained under a common pipeline with three input configurations (multispectral only, multispectral+NDVI, and multispectral+NDRE). Experiments are conducted using the publicly available BLB dataset with performance reported using mean IoU (mIoU), mean F1 (mF1), mean accuracy (mAcc), precision, and recall. U-Net++ with EfficientNet-B3 achieved the highest performance, with an mIoU of 97.62%. SegFormer obtained lower segmentation accuracy but comparable inference speed. Overall, the results indicate that lightweight CNN backbones remain more reliable for operational BLB monitoring while integration of vegetation indices provides small and consistent improvements. The study also highlights the value of standardised UAV datasets to compare disease mapping methods and encourages the use of CNN architectures for field implementation.
Read the full abstract

All authors Yadav Raj Ghimire, Jagrati Talreja, Tewodros Syum Gebre, Timothy Agboada, Shikha V. Chandel, Leila Hashemi Beni

Computer Vision

StoryVideoQA: Scaling Deep Video Understanding with a Large-Scale, Multi-Genre and Auto-Generated Dataset

Zhengqian Wu, Zhixian Liu, Aodong Chen et al. (+6 more)

Video question answering (VideoQA) aims to answer questions about given videos. While existing approaches excel on factoid VideoQA, they struggle with deep video understanding (DVU), which requires the comprehension of complex storylines. This challenge arises from the inherent long-range video content, multi-faceted question types, and instance-level story elements, all of which constrain the scale and diversity of manually constructed DVU datasets. These difficulties constrain the scale and diversity of manually-constructed DVU dataset. To address these, we previously introduced StoryMind to automatically construct DVU datasets with balanced fine-grained topics. Though it can generate high-quality question-answer pairs (QAs) for TV series, it suffers significant performance degradation when handling longer and more complex movies. In this paper, we further design StoryMindv2, an enhanced multi-agent collaboration framework to generate high-quality DVU datasets for both TV series and movies. By integrating a novel supervisor-guided generation mechanism and a refined multi-reviewer voting strategy, the framework is utilized to construct StoryVideoQA, the largest DVU dataset to date, featuring over 363K QAs on 393.2 hours diverse story videos including TV series (avg. 1,635 seconds) and movies (avg. 7,878 seconds). Comprehensive evaluations of 20 state-of-the-art VideoQA methods on this large-scale benchmark reveal that they cannot fully maintain long-range character associations or construct a coherent understanding of complex storylines. To bridge this gap, we propose PlotTree, a novel video understanding agent, re-organizing long-range video content into a hierarchical plot structure, enabling efficient storyline reasoning on StoryVideoQA. Project page: https://github.com/nercms-mmap/StoryVideoQA/
Read the full abstract

All authors Zhengqian Wu, Zhixian Liu, Aodong Chen, Jingyang Zhang, Ruizhe Li, Hanlin Ge, Zhongyuan Wang, Chunxia Xiao, Chao Liang

Computer Vision · Cross-listed from cs.LG

Efficient Mean Curvature Computation on High-Dimensional Data Manifolds

Alexandre L. M. Levada

Estimating local mean curvature at each point of a high-dimensional dataset is a key ingredient of geometry-aware machine learning algorithms, such as the Mean Curvature Boundary Points (MCBP) method. The naive implementation of this computation, based on a local shape operator approximated from k-nearest neighbor patches, involves an explicit construction of a matrix $H$ whose trace form yields an $O(m^4)$ cost per point, rendering the approach intractable for datasets with more than a few dozen features. This paper introduces two complementary contributions that together reduce this cost by several orders of magnitude. The first contribution is an exact algebraic identity. This identity, derived from the orthogonality of the eigenvectors of the covariance matrix and the cyclicity of the trace operator, eliminates $H$ entirely and reduces the per-point cost to $O(m^2)$ after the eigendecomposition. The second contribution addresses the remaining $O(m^3)$ bottleneck of the full eigendecomposition. Since the local covariance matrix has rank at most $k-1 \ll m$, we replace it with a truncated SVD of the $k \times m$ centered data matrix, an $O(k^2 m)$ operation, and derive an analytical approximation for the contribution of the null-space eigenvectors based on the expected value of their outer product under the Haar measure. The resulting estimator has total cost $O(k^2 m + k m p^2)$, where $p = k-1$. Experiments on real-world datasets confirm speedups of 50 to 300 times relative to the original implementation, with negligible loss when the fast estimator is used to replace the original version. By providing a scalable and data-driven estimate of local curvature, the proposed method establishes curvature as a practical geometric feature for a broad range of machine learning tasks, from classical to modern deep learning pipelines.
Read the full abstract

Computer Vision

RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling

Chensheng Dai, Shengjun Zhang, Yifan Li et al. (+3 more)

Video generation models based on Diffusion Transformers (DiTs) have achieved remarkable performance in video synthesis, yet they suffer from high inference latency and computational costs due to the quadratic complexity of 3D attention. Existing acceleration methods primarily reduce computational complexity within each individual denoising steps through techniques such as sparse attention and KV-caching. However, they rigidly adhere to the inherent constraint of the standard diffusion pipeline: every frame in the target video sequence must be subjected to a complete, dense denoising process across all diffusion timesteps. We observe that due to the corresponding contents and motions among adjacent frames, when keyframes with critical semantic transitions are anchored, the intermediate states of others often follow more predictable trajectories, which indicates that such uniform, dense denoising process is inherently redundant for natural video data. To this end, we introduce RhymeFlow, a training-free framework that decouples the denoising trajectories of different frames. Specifically, we first identify a sparse set of pivotal key frames that dominate the latent semantic evolution. Then, only these keyframes undergo dense, step-by-step denoising to ensure structural integrity, while non-keyframes progressively skip denoising steps to minimize computational cost. Since skipped intermediate states of non-keyframes break the temporal coherence in keyframe denoising steps, leading to visual degradation, we further introduce a latent trajectory projection module, which enables keyframes to interact with a complete and temporally consistent sequence representation. Extensive experiments on current DiT-based video generation models demonstrate our method outperforms existing baselines with higher inference speed and better visual quality.
Read the full abstract

All authors Chensheng Dai, Shengjun Zhang, Yifan Li, Zhang Zhang, Zheng Zhu, Yueqi Duan

Computer Vision

Towards One-to-Many Temporal Grounding

Qi Xu, Yue Tan, Shihao Chen et al. (+5 more)

Temporal Grounding (TG) aims to localize video segments corresponding to a textual query. Prior research predominantly focuses on single-segment retrieval. Real-world scenarios, however, often require localizing multiple disjoint segments for a single query – a setting we term One-to-Many Temporal Grounding (OMTG). Previous state-of-the-art MLLMs, optimized for one-to-one settings, struggle in this context, often yielding near-zero scores due to a lack of event cardinality perception. To bridge this gap, we present a systematic solution with three key contributions. First, we establish the first comprehensive OMTG benchmark, introducing Count Accuracy (C-Acc) and Effective Temporal F1 (EtF1) as evaluation metrics. Second, we curate a high-quality OMTG dataset comprising 56k samples through a sophisticated construction pipeline. Third, we develop novel temporal and caption reward functions specifically designed for OMTG. In particular, the caption reward leverages Chain-of-Thought reasoning over dense video captions to explicitly guide policy optimization toward both preciseness and completeness. Extensive experiments show our model achieves a new state-of-the-art EtF1 of 43.65% on OMTG Bench, outperforming Gemini 2.5 Pro and Seed-1.8 by 15.85% and 15.61%, respectively. Project Page: https://insomniaaac.github.io/OMTG/
Read the full abstract

All authors Qi Xu, Yue Tan, Shihao Chen, Jiahao Meng, Anna Wang, Shunping Ji, Hao Fei, Jason Li

Computer Vision

Synthetic Data Generation and Vision-based Wrinkle and Keypoint Detection for Bimanual Cloth Manipulation

Ariel Herrera, Xueyang Kang and Atal Anil Kumar

Robotic manipulation of textiles remains challenging because continuous deformation and self-occlusions hinder the robust visual perception required to estimate the cloth's state. To address the lack of annotated real-world data, we developed a Blender-based synthetic pipeline exporting auto-annotated keypoints, and combined manually labeled renders with real-world data to train a wrinkle detector. We present a perception framework integrating a CNN for permutation-invariant keypoint detection and a YOLOv8-OpenCV pipeline to extract grasping points from structural wrinkles. A proposed bimanual algorithm uses this system to stretch fully folded garments via wrinkles, transitioning to keypoint-based ironing once corners emerge. The keypoint model achieves a Mean Position Error (MPE) of 1.7615 pixels. The perception system transfers to physical fabrics without fine-tuning, outperforming baselines that fail in high-occlusion states or yield false positives on severe folds.
Read the full abstract

Computer Vision

Geodesic Flow Matching on a Riemannian Degradation Manifold for Blind Image Restoration

Akshay Janardan Bankar, Ankita Chatterjee, Sayan Banerjee et al. (+3 more)

Blind image restoration requires recovering clean images from observations corrupted by unknown and potentially mixed degradations. While recent deterministic flow-based methods model restoration as transport processes that map degraded images to clean ones, they typically rely on Euclidean interpolation, implicitly assuming linear degradation geometry. In this paper, we explicitly model degradations as points on a low-dimensional Riemannian manifold and formulate restoration as geodesic transport on the joint image-manifold space. Using a geodesic flow matching objective, we learn intrinsic transport dynamics that respect the curvature of degradation space. This framework generalizes linear flow matching, provides a principled treatment of mixed degradations as geodesic compositions, and yields a clean theoretical interpretation for generalization beyond observed degradations.
Read the full abstract

All authors Akshay Janardan Bankar, Ankita Chatterjee, Sayan Banerjee, Shreyas Pandith, Kalakonda Sai Shashank, Amit Satish Unde

Computer Vision · Cross-listed from cs.RO

RadiusFPS: Efficient Farthest Point Sampling on CPUs and GPUs via Spherical Voxel Pruning

Ziyang Yu, Xiang Li, Qiong Chang et al. (+1 more)

Point clouds are a primary sensory representation for robotic perception, underpinning LiDAR-based autonomous driving, simultaneous localization and mapping (SLAM), and navigation. Within these pipelines, Farthest Point Sampling (FPS) is the most well-known downsampling operator, as its uniform coverage preserves the geometric structure on which downstream perception relies. However, the large time complexity of classical FPS scales poorly with the million-point-per-second rates of modern 3D sensors, making it a dominant latency bottleneck that conflicts with the real-time and limited onboard compute budgets of robotic systems. Therefore, we propose RadiusFPS, an FPS acceleration framework based on spherical voxel pruning that preserves the standard FPS update rule under the same initialization and tie-breaking policy. By indexing the point cloud with spherical voxels, RadiusFPS derives a conservative geometric bound that prunes redundant distance computations in each iteration, complemented by a coordinate-wise point-skip test that removes residual updates. We further introduce RadiusFPS-G, a warp-level GPU implementation that fuses voxel selection, pruning, and distance update into memory-coalesced kernels, eliminating costly global-memory round-trips. On indoor (S3DIS, ScanNet) and outdoor LiDAR (SemanticKITTI) benchmarks, RadiusFPS-G attains up to 2.5x speedup over GPU-based FPS and matches or exceeds QuickFPS among the evaluated methods while using roughly half its GPU memory, with comparable segmentation accuracy. When coupled with the learning-based FastPoint sampler, the resulting pipeline achieves the fastest End-to-End inference among all evaluated configurations. These properties make high-quality FPS-style sampling practical for latency- and memory-constrained robotic vision.
Read the full abstract

All authors Ziyang Yu, Xiang Li, Qiong Chang, Jun Miyazaki

Computer Vision

GRAMformer: Any-Order Modality Interactions via Volumetric Multimodal Cross-Attention

Giordano Cicchetti, Eleonora Grassucci and Danilo Comminiello

Transformer-based multimodal models rely on attention mechanisms to integrate information across heterogeneous modalities. Despite their success, existing multimodal attention formulations compute their scores through collections of pairwise dot-product interactions or by concatenating all the modalities into the keys, even when multiple modalities should be jointly involved. As a consequence, current approaches either incur quadratic complexity in the number of modalities or fail to explicitly model interactions that depend on the joint configuration of multiple representations. In this work, we introduce the Volumetric Multimodal cross-Attention (VMA), a novel cross-attention mechanism in which attention scores are defined as a function of the joint geometry of a query and multiple modality-specific keys. VMA computes the volume spanned by query and key vectors across multiple modalities, capturing joint multimodal dependencies beyond pairwise similarity, enabling native modeling of any-order modality interactions. We integrate VMA into our novel multimodal transformer architecture, named GRAMformer, explicitly designed to integrate any number of modalities. We evaluate the proposed model on multimodal learning tasks, demonstrating improved effectiveness and efficiency.
Read the full abstract

Computer Vision · Cross-listed from cs.CL

Benchmarking Open-Source Layout Detection Models for Data Snapshot Extraction from Institutional Documents

AJ Carl P. Dy and Aivin V. Solatorio

Institutional documents contain substantial amounts of operational and analytical information embedded within figures and tables. Current approaches for extracting visual content from documents are largely built around generic document layout analysis, where figures and tables are treated as uniformly relevant document objects rather than semantically meaningful analytical artifacts. In this work, we introduce a benchmark dataset and evaluation framework for data snapshot extraction, the task of identifying and localizing semantically meaningful visual artifacts within institutional documents. The benchmark spans humanitarian reports, World Bank policy research working papers, and project appraisal documents, and includes annotations for figures and tables that contain reusable analytical information. Using this dataset, we benchmarked multiple open-source layout detection models and evaluated both detection performance and spatial extraction quality. Our results show that current models struggle to generalize to operational institutional documents despite strong performance on conventional academic benchmarks. Common failure modes include confusion between analytical and non-analytical content, fragmentation of composite analytical artifacts, and incomplete extraction of contextual information required for interpretation. These findings highlight a persistent gap between generic document layout analysis and operationally useful data snapshot extraction. We release the source PDFs, annotation dataset, metadata, and source code to support future research in operational document intelligence. The dataset is available at https://huggingface.co/datasets/ai4data/data-snapshot and the source code is available at https://github.com/worldbank/ai4data/tree/main/experimental/data-snapshot.
Read the full abstract

Computer Vision

SAM-Flow: Source-Anchored Masked Flow for Training-Free Image Editing

Haowang Cui, Rui Chen, Tao Luo et al. (+3 more)

Training-free image editing has recently attracted increasing attention due to its ability to modify real images using powerful pre-trained diffusion and flow-matching models without additional training. However, existing inversion-based and differential-flow-based methods usually perform global latent transport, which inevitably propagates editing effects to non-target regions and leads to background leakage. To address this problem, we propose SAM-Flow, a source-anchored masked flow framework for localized training-free image editing. Instead of updating the whole latent representation, SAM-Flow first uses a scout image and token-grounded attention maps to localize the editable semantic regions. It then applies differential velocity updates only within these regions, while anchoring the remaining areas to the source-image latent trajectory. To further improve spatial stability and boundary naturalness, we introduce a time-varying source-anchored projection mechanism with dynamic soft masks, transition regions, and temporal mask accumulation. The proposed method is plug-and-play and can be integrated with mainstream flow-matching backbones such as Stable Diffusion 3 and FLUX without any fine-tuning. Extensive qualitative and quantitative experiments demonstrate that SAM-Flow achieves accurate semantic editing while significantly improving background preservation, providing a simple and general localized editing paradigm for training-free image editing. Code is available at: https://github.com/chwbob/Sam-Flow.
Read the full abstract

All authors Haowang Cui, Rui Chen, Tao Luo, Tao Guo, Zheng Qin, Jiaze Wang

Computer Vision

Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology

Yanqing Luo, Julius Hense, Niklas Prenißl et al. (+4 more)

Explanations of multiple instance learning (MIL) models are widely used for validation and discovery in digital histopathology. Existing methods primarily rely on heatmaps that highlight influential regions but do not explain how evidence from different tissue regions is combined to produce a prediction. This limits interpretability, especially when decisions depend on interactions between tissue features. We introduce Symbolic explainable MIL (Symb-xMIL), a post-hoc explanation framework that quantifies how a MIL model's behavior aligns with human-readable decision rules, expressed as logical relationships (e.g., AND, OR, NOT) between input features. These alignment scores reveal semantic patterns underlying the model's predictions. We evaluate Symb-xMIL on synthetic and real-world histopathology datasets. On synthetic MIL data, Symb-xMIL reliably recovers ground-truth logical rules. In a clinical tumor detection task, the best-aligned rules uncover heterogeneous decision patterns and expose hidden model errors. On an HPV-prediction task on TCGA-HNSCC, a cohort of head and neck cancer, our framework refines patient survival stratification beyond HPV status with potential clinical relevance. Overall, Symb-xMIL extends MIL explainability beyond visual attribution toward structured, rule-based reasoning, enabling more transparent and semantically grounded interpretation of model predictions.
Read the full abstract

All authors Yanqing Luo, Julius Hense, Niklas Prenißl, Andreas Mock, Klaus-Robert Müller, Thomas Schnake, Mina Jamshidi Idaji

Computer Vision

DisasterBench: A Multimodal Benchmark for UAV-Based Disaster Response in Complex Environments

Tan Zhang, Quanyou Li, Lu Zhang et al. (+3 more)

When a disaster unfolds, responders must answer not only what is happening, but also why it is happening, what will happen next, and what to do now, often from noisy low-altitude UAV views and under tight on-site compute constraints. However, most existing multimodal benchmarks emphasize perception (e.g., recognition/description), cover limited disaster types, and provide insufficient support for the multi-stage reasoning required in practical emergency response. We introduce DisasterBench, a multi-stage multimodal reasoning benchmark for UAV-Based disaster response in complex environments. DisasterBench spans 14 disaster-related scene types and 9 response-critical tasks across pre-, during-, and post-disaster stages, with fine-grained disaster-task mappings that explicitly test causal attribution, propagation prediction, damage analysis, and decision-oriented reasoning. To enable reasoning on the edge, we further propose DisasterVL, a lightweight multimodal model optimized with a three-stage pipeline combining domain instruction tuning, chain-of-thought-guided multimodal alignment, and reinforcement learning-based policy optimization. Experiments across 21 popular MLLMs show that our 2B-parameter DisasterVL outperforms all evaluated open-source models and substantially narrows the gap to state-of-the-art closed-source models, achieving GPT-4o-comparable reasoning accuracy with superior efficiency. The project page is available at https://github.com/TanmouTT/DisasterBench.
Read the full abstract

All authors Tan Zhang, Quanyou Li, Lu Zhang, Jun Liu, Xiaofeng Zhu, Ping Hu

Computer Vision

SC-MFJ: A Simple Haptic Quality Metric for Medical Image Segmentation

Souraj Adhikary, Negar Chabi and Andre Mastmeyer

Standard segmentation metrics such as Dice and Hausdorff distance measure geometric overlap but say nothing about whether a segmented surface is suitable for haptic rendering in surgical simulation. We propose SC-MFJ (Surface-Constrained Mean Force Jerk), a simple, inexpensive metric that samples a segmented organ surface with many short virtual stylus walks and measures how jerky the resulting contact forces are. The metric is computed from existing segmentation outputs and uses roughly one minute of CPU time per case. We evaluate three pancreas CT segmentation approaches-binary nnU-Net output, Gaussian-smoothed output, and learned signed distance function (SDF) regression-across 80 cases in five-fold cross-validation. SC-MFJ reveals a 147x gap in haptic quality between the raw binary baseline and simple Gaussian post-processing, a difference entirely invisible to Dice and HD95. It also shows that learned SDF regression, despite requiring full model retraining, produces more variable haptic quality than Gaussian smoothing, with a case-level standard deviation of 168 N/s2 compared with 22 N/s2 for Gaussian. A second evaluation on the LiTS liver dataset (131 cases) confirms the generality of these findings: the binary-to-Gaussian gap widens to 189x, and Gaussian smoothing again produces consistently low force jerk across all folds. Our results suggest that for haptic simulation applications, a one-line post-processing step may be sufficient, and that a cheap metric like SC-MFJ can flag problems that geometric metrics miss.
Read the full abstract

Computer Vision · Cross-listed from cs.RO

ActiveMimic: Egocentric Video Pretraining with Active Perception

Xingyao Lin, Guojin Zhong, Tianyi Lu et al. (+4 more)

Egocentric human video offers a scalable alternative to robot data for pretraining, yet models pretrained on such video consistently underperform those pretrained on robot data. We attribute this gap to a missing signal, the active perception behavior in egocentric videos, where humans continuously reposition their viewpoint during manipulation, inducing camera motion that standard pipelines treat as noise. To address this, we present ActiveMimic, a pretraining framework that recovers synchronized camera and wrist trajectories from a single body-worn RGB camera, models camera motion as a viewpoint action, and jointly learns active perception and manipulation from in-the-wild egocentric human video before adapting to a target robot. Empirically, real-world experiments across tasks with diverse active perception demands show that ActiveMimic consistently surpasses baselines pretrained on human video and matches state-of-the-art models pretrained on robot data. Further analysis provides evidence that active perception capability originates from egocentric human video pretraining rather than robot-specific fine-tuning, confirming active perception as the key to unlocking egocentric human video for robot pretraining.
Read the full abstract

All authors Xingyao Lin, Guojin Zhong, Tianyi Lu, Ziyi Ye, Yichen Zhu, Zuxuan Wu, Yu-Gang Jiang

Computer Vision

Adversarial Attacks Already Tell the Answer: Directional Bias-Guided Test-time Defense for Vision-Language Models

Liangsheng Liu, Si Chen, Jiamin Wu et al. (+5 more)

Vision-Language Models (VLMs), such as CLIP, have shown strong zero-shot generalization but remain highly vulnerable to adversarial perturbations, posing serious risks in real-world applications. Test-time defenses for VLMs have recently emerged as a promising and efficient approach to defend against adversarial attacks without requiring costly large-scale retraining. In this work, we uncover a surprising phenomenon: under diverse input transformations, adversarial images in CLIP's feature space consistently shift along a dominant direction, in contrast to the dispersed patterns of clean images. We hypothesize that this dominant shift, termed the Defense Direction, opposes the adversarial shift, pointing features back toward their correct class centers. Building on this insight, we propose Directional Bias-guided Defense (DBD), a test-time framework that estimates the Defense Direction and employs a DB-score-based two-stream reconstruction strategy to recover robust representations. Experiments on 15 datasets demonstrate that DBD not only achieves SOTA adversarial robustness while preserving clean accuracy, but also reveals the counterintuitive result that adversarial accuracy can even surpass clean accuracy. This demonstrates that adversarial perturbations inherently encode directional priors about the true decision boundary.
Read the full abstract

All authors Liangsheng Liu, Si Chen, Jiamin Wu, Weiwei Feng, Zhixin Cheng, Xiaotian Yin, Wenfei Yang, Tianzhu Zhang

Computer Vision

RQUL-UIE: Revitalizing Quality-Unstable Labels for Underwater Image Enhancement via In-Dataset Self-Supervision

Haochen Hu, Yanrui Bin, Chih-yung Wen et al. (+1 more)

Underwater Image Enhancement (UIE) is essential for mitigating degradations caused by water medium. Although learning-based methods have advanced significantly, most rely on paired datasets with unstable label quality, which bottlenecks model performance. This paper proposes a diffusion-based, in-dataset self-supervised learning strategy designed to exploit the quality distribution of training labels. Specifically, we evaluate label quality via semantic perception embeddings from a pre-trained diffusion model in a training-free manner. These quality scores are subsequently quantized into noise-level indices, guiding a multi-step denoising process for level-wise supervision. This mechanism prevents low-quality labels from degrading the model while maximizing their utility during training. Furthermore, a Fourier-based refinement network is incorporated to explicitly reconstruct high-frequency components. Extensive evaluations demonstrate that our method consistently outperforms SOTA approaches in restoration quality. The code and pre-trained model will be available once accepted in link.
Read the full abstract

All authors Haochen Hu, Yanrui Bin, Chih-yung Wen, Bing Wang

Computer Vision

Adaptive Tokenisation Via Temporal Redundancy Masking And Latent Inpainting

Kevin Dave, Sai Aditya Patkuri, Chhaya Kumar Das et al. (+3 more)

Adaptive video tokenisation seeks to dynamically allocate token budgets based on the underlying visual complexity of a sequence. Current continuous-regime approaches achieve this via iterative binarised searches or trained neural regressors, while discrete methods often require a full-rate decoder pass to estimate information content. We demonstrate that such computational overheads are not strictly necessary. We show that the latent space of a frozen continuous video tokeniser inherently encodes temporal redundancy that can be exploited directly: spatial positions whose latent representations change minimally between consecutive frames carry near-zero additional information. We introduce a parameter-free adaptive token allocation mechanism that applies a fixed threshold to per-position temporal-L1 differences, identifying and dropping redundant latent positions. Consequently, the compression rate emerges naturally from the input content rather than being enforced top-down: static scenes get compressed aggressively, while highly dynamic sequences retain more tokens. To reconstruct the dropped positions, we propose the Latent Inpainting Transformer (LIT), a lightweight factorised spatial-temporal attention architecture. The resulting inference pipeline is highly efficient, requiring only a single encoder pass and one LIT forward pass, eliminating the need for auxiliary routing networks. Evaluations across TokenBench and DAVIS, which are the standard benchmarks used by recent tokenisers~\cite{infotok, agarwal2025cosmos}, indicate that our framework yields meaningful, content-driven token allocation while maintaining competitive reconstruction fidelity, and delivers a $31\times$ inference-time speedup over the continuous adaptive baseline (ElasticTok-CV) and an $\approx2\times$ speedup over the discrete information-theoretic baseline (InfoTok).
Read the full abstract

All authors Kevin Dave, Sai Aditya Patkuri, Chhaya Kumar Das, Gouranga Bala, Rajeshkumar SA, R. Venkatesh Babu

Computer Vision · Cross-listed from cs.RO

AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding

Qize Yu, Jiadi You, Yuran Wang et al. (+12 more)

Vision-Language-Action (VLA) models leverage the rich world knowledge of pretrained vision-language models (VLMs) to enable instruction-following robotic manipulation. However, the structural mismatch between VLM semantic spaces and embodied control policies often hinders the learning of precise perception-action mappings. To address this challenge, we propose AffordanceVLA, a scalable, unified framework that introduces structured affordance learning as a task-oriented and object-centric intermediate representation to establish a more precise and robust perception-action mapping. Specifically, we progressively model manipulation priors through three complementary components - Which2Act, Where2Act, and How2Act - which jointly produce spatially grounded, semantically conditioned, and action-coupled intermediate representations, thereby naturally bridging vision, language, and action. We integrate these modules into a Mixture-of-Transformer (MoT) architecture and adopt a three-stage progressive training curriculum that leverages 8.8M affordance-centric grounding and pointing samples, translating scalable vision-language supervision into improved robotic manipulation. To overcome the scarcity of dense affordance labels in robotic datasets, we also develop a robust automated data augmentation pipeline. Extensive experiments on ID & OOD simulation and real-world demonstrate that AffordanceVLA outperforms strong VLA baselines across diverse manipulation scenarios, validating structured affordance learning as a scalable and robust bridge that integrates multi-source vision-language supervision while connecting pretrained VLM semantics to embodied robot control.
Read the full abstract

All authors Qize Yu, Jiadi You, Yuran Wang, Jiaqi Liang, Bowen Ping, Yang Tian, Yue Chen, Bohan Zhou, Wenxuan Song, Minghong Cai, Zeying Gong, Ruihai Wu, Yinchuan Li, Junwei Liang, Yingcong Chen

Computer Vision

Computation-Aware Event-to-Frame Reconstruction via Selective Attention

Jingqian Wu, Yunbo Jia and Edmund Y. Lam

Event-to-frame (E2F) reconstruction bridges asynchronous event streams with frame-based vision pipelines, but existing methods often face a trade-off between reconstruction quality and computational efficiency. In this work, we propose an efficient E2F framework that emphasizes causal temporal modeling and computation-aware design. The architecture adopts a recurrent encoder-decoder to incrementally aggregate event information with compact hidden states. To improve robustness under fast motion and illumination variations, a selective context fusion strategy is introduced to integrate event-driven features with prior intensity cues. Within this fusion process, a lightweight hybrid attention mechanism enhances feature selectivity without relying on heavy attention operations. Experimental results on standard benchmarks demonstrate that the proposed approach achieves competitive reconstruction performance while maintaining a favorable balance between accuracy and model complexity.
Read the full abstract

Computer Vision

Diff-CA: Separating Common and Salient Factors with Diffusion Models

Michaël Soumm, Alexandre Fournier Montgieux, Yunlong He et al. (+2 more)

Contrastive Analysis aims to separate factors that are common between two data distributions from those that are salient to only one of them. Existing contrastive methods are based on generative models (e.g., VAEs or GANs) that often suffer from limited reconstruction and image quality, which hampers effective latent factor separation and limits their applicability to high-fidelity image generation and edition. We propose a novel conditioning framework for diffusion models that enables contrastive decomposition without compromising generation quality. We first train a prompt-free, image-conditioned diffusion model, and then learn to decompose the conditioning into a common and a salient factor, using weak supervision. We prove that the additive contrastive factorization, commonly assumed in prior work, is identifiable under mild conditions. This factorization enables targeted operations by swapping or interpolating only the salient factor.
Read the full abstract

All authors Michaël Soumm, Alexandre Fournier Montgieux, Yunlong He, Pietro Gori, Alasdair Newson

Computer Vision

Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback

Huaisong Zhang, Hao Yu, Yuxuan Zhang et al. (+7 more)

Despite generating increasingly photorealistic images, text-to-image (T2I) models still exhibit localized, subtle, and structurally complex failures. Diagnosing these failures requires instance-level feedback that answers where a defect occurs, what type it is, why it is defective, and its importance to overall image quality. While recent dense-feedback methods move beyond scalar supervision, their heatmap-centric representations still formulate diagnosis as pixel-field regression, making it difficult to localize variable-cardinality defects and bind semantic reasons to individual failures. To address this representation bottleneck, we propose Structured Defect Grounding (SDG), which casts T2I diagnosis as structured set prediction by modeling each defect as a (location, type, reason, importance) tuple. To make this formulation trainable and measurable, we introduce SDG-30K, a 30K-image dataset with box-grounded annotations across four modern T2I generators, together with a dedicated evaluation protocol, SDG-Eval. Building on this structured representation, we further present a diagnosis-to-alignment framework in which a Vision-Language Model (VLM) serves as the SDG detector, and BoxFlow-GRPO converts predicted defect sets into box-derived, importance-weighted spatial rewards for diffusion model alignment. Extensive experiments show that our SDG detector outperforms leading proprietary VLMs on structured defect grounding, while SDG-guided rewards consistently improve T2I alignment and support localized image refinement. These results establish SDG as a unified, instance-level interface for diagnosing, evaluating, and enhancing modern generative models.
Read the full abstract

All authors Huaisong Zhang, Hao Yu, Yuxuan Zhang, Jiahe Wang, Xinrui Chen, Haoxiang Cao, Feng Lu, Wendong Zhang, Changqian Yu, Chun Yuan

Computer Vision

MS-DKC: A Dataset Knowledge Card Framework for Designing and Adapting Medical Image Segmentation Models

Tariq M. Khan, Syed Saud Naqvi, Thantrira Porntaveetus et al. (+4 more)

Medical image segmentation is often framed as a search for stronger architectures, but this can obscure a more fundamental question: what does the dataset require from the model? In medical imaging, this requirement is shaped by foreground occupancy, morphology, boundary ambiguity, topology sensitivity, annotation quality, acquisition variation, and operating point. This paper introduces the Medical Segmentation Dataset Knowledge Card (MS-DKC), a framework for making these factors explicit. MS-DKC records dataset evidence through image/acquisition, morphology, supervision, context-dependence, and deployment-risk descriptors. These descriptors are mapped to failure modes, design priors, and risk-aligned criteria, making segmentation design more traceable than architecture-first comparison. We evaluate MS-DKC on DRIVE, ISIC2018, and ACDC, representing distinct regimes. DRIVE contains sparse, thin, branching vessels, favoring detail-preserving models, sensitivity-aware optimization, threshold analysis, and topology-aware metrics. DKC-TNet-v2 achieved Dice 0.8044 and IoU 0.6730 with 35103 parameters, while SA-UNetv2-DKC-AmbRef reached Dice 0.8141, IoU 0.6865, sensitivity 0.8265, specificity 0.9804, and AUC 0.9853. ISIC2018 involves compact but appearance-variable lesions; validation-constrained score-function selection on Att-Next-Topo/ATTNext produced MS-DKC-AttNextTopo-VCSF-NoAug with Dice 0.8872, IoU 0.8214, precision 0.9173, Boundary F1 0.4878, and ASSD 4.13, while plausible additions failed to improve the risk-aligned profile. ACDC provides a multi-class cardiac case, where MS-DKC recommends four-class softmax segmentation, class-balanced Dice/CE supervision, and class-wise surface evaluation. Overall, the results support dataset-conditioned design: different datasets require different priors, operating points, and evidence before a model can be judged appropriate.
Read the full abstract

All authors Tariq M. Khan, Syed Saud Naqvi, Thantrira Porntaveetus, Hamid Alinejad-Rokny, Shahzaib Iqbal, Imran Razzak, Mohammad AU Khan

Computer Vision

HyperVis: Continuous Latent Visual Relational Graphs on the Lorentz Hyperboloid for Compositional Reasoning

Moshiur Farazi, Sameera Ramasinghe, Mahbub Ahmed Turza et al. (+1 more)

Vision-Language Models (VLMs) struggle with compositional reasoning that requires understanding inter-object relationships. A natural remedy is to inject explicit scene graph triplets $\langle s, p, o \rangle$ from an off-the-shelf scene graph generator (SGG), but we show this backfires: discrete text labels collide with the continuous visual modality, degrading GQA accuracy from 60.38% to 58.86%. We propose HyperVis, which bypasses the SGG semantic bottleneck entirely. From $N$ class-agnostic region proposals, we compute a dense $O(N^2)$ visual relation tensor via spatially-biased cross-attention, project it onto a Lorentz hyperboloid, and enforce hierarchy through spatial physics, namely IoA-driven entailment cones and exterior-angle repulsion. We discover that HyperVis contributes in two complementary ways: (1) as a training-time regularizer, the hyperbolic relational losses shape LoRA representations that improve generative VQA (GQA 61.03% vs.\ 57.21% for LoRA fine-tuning without relational losses, recovering and surpassing the baseline); and (2) as an inference-time relational encoder, hyperbolic prefix tokens boost discriminative compositional scoring (SugarCrepe 79.94%, $+$6.25pp over baseline). The learned curvature stabilises at $\kappa{=}4.0$, an order of magnitude above prior hyperbolic VLMs where $\kappa$ typically collapses toward zero, indicating that continuous visual features genuinely require the exponential volume of strongly curved space. A controlled Euclidean ablation confirms this decomposition: the relational pipeline regularises LoRA comparably in flat space (GQA 60.81%), but the compositionality gain is specifically hyperbolic (SugarCrepe $+$4.58pp over Euclidean), with entailment loss ${\sim}6{\times}$ higher in Euclidean training. Codes are available at TBA.
Read the full abstract

All authors Moshiur Farazi, Sameera Ramasinghe, Mahbub Ahmed Turza, Shafin Rahman

Computer Vision

Knowledge Distillation for Visual Autoregressive Models

Elia Peruzzo, Aritra Bhowmik, Guillaume Sautiere et al. (+2 more)

Autoregressive (AR) image generation models are highly expressive but computationally intensive, motivating effective model compression. Knowledge distillation (KD) is a natural approach for model compression and has been widely studied in language modeling, yet its behavior in visual AR generation remains underexplored. In this work, we present the first systematic study of distillation strategies for AR image models. Our analysis shows that while standard distillation can yield meaningful gains, recent methods developed for language do not directly transfer to images: long decoding horizons and visual token ambiguity make teacher supervision unreliable especially under student-conditioned contexts. To address this, we propose VarKD, a distillation framework for visual autoregressive models that distills on student samples while selectively applying teacher supervision and reducing token-level ambiguity. Experiments on ImageNet across multiple AR backbones show that VarKD consistently outperforms prior distillation baselines, narrowing the gap to large-scale models.
Read the full abstract

All authors Elia Peruzzo, Aritra Bhowmik, Guillaume Sautiere, Yuki M Asano, Amirhossein Habibian

Computer Vision · Cross-listed from cs.AI

Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation

Haocheng Luo, Jiahui Liu, Ruicheng Zhang et al. (+8 more)

While Vision-Language Models excel at general multimodal understanding, they still struggle with visual spatial planning. We attribute this limitation to a perception–reasoning modality gap. Visual planning requires models to infer latent state structures from pixels and then reason over the recovered structure to produce valid actions, whereas symbolic planning directly leverages explicit representation. This discrepancy introduces two sequential bottlenecks: visual state recovery at the perception stage and multi-step planning at the reasoning stage. To address this, we propose MGSD, a two-stage modality-gap-aware self-distillation framework. First, a cold-start grounding stage establishes reliable visual state recovery before on-policy training. Second, a symbol-guided on-policy self-distillation stage transfers the privileged teacher's planning behavior to the student through token-level supervision on student-generated prefixes. Crucially, symbolic information is used only during training, while inference relies exclusively on visual inputs. Experiments on visual planning benchmarks show that MGSD consistently improves performance across different model scales, raising the macro average by 19.3% and 18.4%, respectively. The resulting models substantially reduce the gap to the upper bounds obtained with symbolic inputs. Ablation studies and diagnostic analyses further confirm that the gains arise from improvements in both visual state recovery and optimal-path reasoning. These results demonstrate that MGSD strengthens not only the recovery of actionable states from visual observations but also the ability to plan over the inferred structures. Code is available at https://github.com/Oranger-l/MGSD.
Read the full abstract

All authors Haocheng Luo, Jiahui Liu, Ruicheng Zhang, Zhizhou Zhong, Jiaqi Huang, Zunnan Xu, Quan Shi, Jun Zhou, Shuiyang Mao, Wei Liu, Xiu Li

Computer Vision

VZCrash: A Large-Scale IMU Dataset of Ego-Vehicle Crashes

Tommaso Bianconcini, Henrique Piñeiro Monteagudo, Aurel Pjetri et al. (+2 more)

We introduce VZCrash, the largest publicly available dataset of real-world vehicle collision data featuring Inertial Measurement Unit (IMU) telemetry. The dataset contains more than 31,000 validated crashes and 158,000 negative samples, including hard cases and distractors. Each sample includes acceleration and angular velocity at 100 Hz, and GPS speed at 1 Hz. Events in VZCrash were captured by devices installed on a fleet of 73,010 commercial vehicles of different sizes driving in the United States over the span of several years. We also present an extensive experimental study enabled by the volume of the dataset. We first benchmark several different approaches, from a simple threshold-based heuristic to state-of-the-art deep learning models. Then, we present an experiment demonstrating the importance of scaling data to train high-quality crash detection models, and we show that scale is especially important when these models need to be deployed into a real-world environment.
Read the full abstract

All authors Tommaso Bianconcini, Henrique Piñeiro Monteagudo, Aurel Pjetri, Tomaso Trinci, Leonardo Taccari

Computer Vision

FontFusion: Enhancing Generative Text in Diffusion Models with Typographic Conditioning

Marian Lupascu, Nipun Jindal, Ionut Mironica et al. (+1 more)

Typography generation in diffusion models faces a persistent trade-off: enabling precise font control typically degrades text legibility, while maintaining readability often sacrifices typographic fidelity. We present FontFusion, a plug-and-play conditioning framework for Diffusion Transformer (DiT) architectures that resolves this dilemma through three core innovations: (1) a hierarchical token representation establishing explicit text-font relationships at multiple granularities, (2) position-aware embeddings creating spatial bindings between typography and image content, and (3) a multi-level token dropping strategy improving both computational efficiency and generalization to unseen fonts. Our systematic evaluation of font embedding spaces reveals that a dual encoder combining DeepFont and DINOv2 outperforms any single encoder for typography tasks. FontFusion demonstrates 76% relative improvement on challenging decorative fonts over single-encoder baselines and font consistency gains exceeding approximately 68-76% over unconditioned models, while integrating into existing DiT architectures without retraining.
Read the full abstract

All authors Marian Lupascu, Nipun Jindal, Ionut Mironica, Zhaowen Wang

Computer Vision

ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE

Mishan Aliev, Eva Neudachina, Ilya Bykov et al. (+4 more)

Modern diffusion models generate high-quality images and videos, but their iterative denoising process makes inference expensive. Feature caching accelerates sampling by reusing or predicting intermediate activations across neighboring denoising steps, exploiting the redundancy of computations along the reverse trajectory. In this work, we focus on the caching schedule: selecting which denoising steps should be fully recomputed. Existing schedules are either fixed (e.g. uniform) or chosen adaptively from per-step error heuristics; in both cases, the actual compute cost is a side-effect of hand-tuned thresholds rather than a quantity the user can specify. We propose ReCache, which inverts this: given a target budget k, it learns the recomputation schedule that maximizes generation quality, turning compute into a directly controllable input. ReCache trains via policy gradients, sidestepping backpropagation through full diffusion inference, and uses no labelled data. Generations from uncached inference serve as matching targets, paired with a reward for generation quality. ReCache is compatible with any caching mechanism, including feature reuse and feature forecasting; for each mechanism, a single trained policy adapts across computational budgets at inference time. ReCache consistently outperforms scheduling baselines: under a $\times5.04$ FLOPs reduction on FLUX, it reduces LPIPS by 31% (from 0.456 to 0.316) compared to DiCache; on Wan 2.1 at a $\sim \times2.6$ speedup, it drops LPIPS by 65% (from 0.480 to 0.169) and boosts the VBench score by 7% (5.6 points, from 70.4 to 76.0) over uniform HiCache. Code is available at https://github.com/thecrazymage/ReCache.
Read the full abstract

All authors Mishan Aliev, Eva Neudachina, Ilya Bykov, Aleksandr Oganov, Kirill Struminsky, Aibek Alanov, Denis Rakitin

Computer Vision

LLM-Conditioned Synthesis of Pathological Gaits via Structured Gait-Language Representations

Mritula Chandrasekaran, Sanket Kachole, Jarek Francik et al. (+1 more)

Pathological gait datasets remain scarce due to privacy, recruitment, cost, and movement variability. Our work presents a multimodal LLM-guided framework for pathology-aware 3D gait data synthesis from structured textual descriptions. The proposed method generates fixed-length synthetic skeleton-based gait sequences for pathological gait classification tasks. The framework combines motion tokenisation, pathology-aware language conditioning, LLM-based semantic augmentation, and language-to-gait generation. A key contribution is the proposed pathological tokeniser, which is designed to preserve pathology-specific motion characteristics during discrete representation learning. Experiments suggest that the proposed synthetic sequences improve downstream classification for recurrent classifiers when combined with real data. The best result is obtained using a GRU classifier trained with real and synthetic samples, achieving 92.77% accuracy under a leave-one-subject-out protocol.
Read the full abstract

All authors Mritula Chandrasekaran, Sanket Kachole, Jarek Francik, Dimitrios Makris