cs.CV · 2026-08-28 · No. 98
Computer Vision and Pattern Recognition, 2026-08-28.
19 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
19 entries-
01
LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics
Lukas Kuhn, Lucas Maes, Giuseppe Serra, Quentin Le Lidec, Yann LeCun, Randall Balestriero, Florian Buettner
cs.CV · cs.AI
Video carries the temporal structure of the physical world, yet learning representations from it has remained computationally expensive: prevailing self-supervised methods either prevent representation collapse through architectural asymmetries, coupling an exponential-moving-average target encoder, a stop-gradient, and a capacity-limited predictor, or circumvent it by reconstructing masked content in pixel space. We introduce LeVJEPA, the...
-
02
Successive Capacity Growth: Task-Complexity-Driven Width and Depth Expansion for Vision Transformer Encoders in JEPA World Models
Frederik Berenz
cs.CV · cs.AI
Joint-Embedding Predictive Architectures (JEPAs) for world modeling typically employ fixed-size Vision Transformer encoders that are over-provisioned for simple tasks and under-provisioned for complex ones, with significant redundancy across attention heads. We propose Successive Capacity Growth (SCG), a method that starts from a minimal encoder (1 head, 2 layers, 283K parameters) and grows incrementally in width (adding attention heads for...
-
03
KnockGS:interaction-Grounded Calibrationof Physical Gaussian Representations
Chenchen Ge, Hanwen Shen, Bowen Jing, Jiyuan Cai, Xiaofeng Wang, Hongsen Lei, Weitao Zhou, Dandan Zhang, Haibao Yu
cs.CV · cs.AI
Physics-integrated 3D Gaussian representations now allow reconstructed deformable objects to be simulated and rendered under explicit material models. Existing pipelines, however, assume that material parameters are known or manually specified, limiting their applicability when these parameters must be inferred from observed object dynamics. We propose KnockGS, an interaction-response PhysicalGS framework that estimates the elasticity and...
-
04
PAWBench: How Far Are We from Probabilistically Aligned World Modeling?
Yuandong Pu, Le Zhuo, Sayak Paul, Gabriel Jorge Menezes, Avram Đorđević, Shiyang Li, Yifan Zhou, Bin Fu, Wenlong...
cs.CV · cs.AI
Recent video generation models are increasingly framed as world models. Many physical processes can unfold in more than one valid way. Therefore, a world model should reproduce not only a plausible trajectory, but also the distribution of possible behaviors under the same initial observation and action. We call this distribution-level requirement probabilistic alignment. However, existing evaluations largely assess individual-video...
-
05
TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detection
Su Wang, Yaochen Li, Min Yang, Jiaohao Nie, Chang Liu, Yuehu Liu
cs.CV · cs.AI · cs.RO · eess.SY
Most single-stage 3D object detectors complete different tasks with the same extracted features. Nevertheless, it is impossible to project features into a common space that is adaptive for all the tasks. We present a novel task-aware deformable prediction (TADP) method for single-stage 3D object detection to solve this problem. Firstly, a triple feature refinement aggregation module is designed to extract three-level features adaptively....
-
06
PACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inference
Junjie Liu, Shengyuan Ye, Xu Chen
cs.CV · cs.AI
Vision-Language Models (VLMs) demonstrate exceptional visual reasoning capabilities, yet their inference costs escalate rapidly with the proliferation of visual tokens. Existing visual token pruning methods exhibit two fundamental limitations. First, most approaches operate exclusively post-vision encoder, leaving the substantial latency of the visual encoding phase unoptimized. Second, under strict token budgets, these methods often fail to...
-
07
Beyond Classification: Task-Dependent Learnability under Privacy-Motivated Image Transformations
Leon Ranke, Wolfgang Hübner, Ronny Hug, Michael Arens, Jürgen Beyerer
cs.CV · cs.AI · cs.LG
Privacy-Enhancing Technologies (PETs) in computer vision often rely on noise or image perturbations to protect visual data while securely processing it, creating a trade-off between task performance and protection. This trade-off is commonly evaluated using image classification, which primarily captures semantic separability and remains robust despite significant geometric, spatial layout or local boundary alterations. As a result, it is too...
-
08
Multi-Person Human Motion Forecasting in Complex Scenes
Serdar Ozsoy, Lars Doorenbos, Juergen Gall
cs.CV · cs.AI
Accurately forecasting the movement of people in complex scenes requires reasoning over the past and present state of the entire environment. In this context, effectively incorporating object information and social interactions into a unified framework remains particularly challenging. To address this, we propose Object-Conditioned Social Diffusion (OCSD), a conditional diffusion model that integrates motion history, multi-person...
-
09
Per-View Gaussian Predictions Enable Training-Free Distractor Filtering in Feed-Forward 3DGS
Kangmin Seo, Jae-Pil Heo
cs.CV · cs.AI
Feed-forward 3D Gaussian Splatting reconstructs an explicit Gaussian representation from multiple input images in one network execution, making 3D reconstruction increasingly accessible for casual captures. However, such captures frequently contain transient objects that appear in only a subset of the views. Such content can be encoded into the per-view Gaussians associated with the inputs that observe it and remain in the combined...
-
10
From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and Segmentation
Haowen Gu, Gensheng Pei, Junzhu Mao, Qiong Wang, Mingwu Ren, Yazhou Yao
cs.CV · cs.AI
Although Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in Medical Visual Question Answering (Med-VQA), their reliance on global image features often lacks precise pixel-level grounding, thereby limiting clinical trustworthiness. To bridge the semantic gap between high-level clinical reasoning and spatial localization, we propose \textsc{\textsc{MedREAL}} (\textbf{Med}ical \textbf{RE}asoning-driven...
-
11
MedFG-VQA: Low-Frequency Memory and Graph Attention for Lightweight Medical VQA
Haowen Gu, Gensheng Pei, Zeren Sun, Mingwu Ren, Xiangbo Shu, Yazhou Yao, Fumin Shen
cs.CV · cs.AI
Medical Visual Question Answering (Med-VQA) holds significant promise for clinical decision support, yet faces challenges due to limited annotated data and the high computational demands of existing large vision-language models. We propose MedFG-VQA, a lightweight framework that leverages a memory bank to augment DCT-based low-frequency features and employs graph-enhanced cross-attention for effective visual-textual alignment. Specifically,...
-
12
Hyperspectral Diffusion Equivariant Imaging (HyDiff-EI): A Self-supervised Framework for Hyperspectral Image Inpainting
Shuo Li, Mike Davies, Mehrdad Yaghoobi
cs.CV · cs.LG
A novel Hyperspectral diffusion Equivariant Imaging (HyDiff-EI) framework for solving the hyperspectral image (HSI) inpainting problem has been presented here. Unlike conventional diffusion-based methods that rely on large-scale pretraining, HyDiff-EI is a test-time optimization framework that learns directly from a single corrupted HSI acquisition. This makes it flexible for different sensor configurations and particularly well-suited for...
-
13
Generative Semantic Scene Completion
Shi Chen, Weifeng Ge
cs.CV · cs.LG · cs.RO
Outdoor LiDAR semantic scene completion (SSC) recovers a dense semantic voxel grid from a scan observing 1% of the target volume, under class imbalance beyond 7,000x. We recast SSC as generative semantic scene completion (GSSC): a single discrete-diffusion formulation in three roles. First, paired sparse-dense scene synthesis (PS$^3$) generates matched sparse LiDAR observations with their dense semantic completions, addressing the long tail...
-
14
LiveVVT: High-Fidelity Video Virtual Try-On in Real Time
Yushe Cao, Shikun Feng, Ruxiang Duan, Liyong Wang, Dianxi Shi, Chun Yu, Junliang Xing
cs.CV · cs.AI
Diffusion-based Video Virtual Try-On (VVT) achieves high visual fidelity through bidirectional spatio-temporal modeling, but complete-clip dependence incurs prohibitive latency and computational overhead in practical continuous deployment. Naively enforcing causality disrupts pretrained bidirectional priors and substantially degrades synthesis quality. We introduce LiveVVT, a rolling streaming diffusion framework that preserves bounded...
-
15
AesCanvas: A Large-Scale Dataset and Benchmark for Aesthetic Critique and Contextual Suitability
Xuanwei Hu, Haoyu Dong, Kejun Wu, Tianyi Liu, Jianjun Gao
cs.CV · cs.AI
Recent advances in Multimodal Large Language Models (MLLMs) have extended Image Aesthetic Assessment (IAA) beyond scalar scores toward interpretable critique and guidance. Yet existing benchmarks mainly assess intrinsic visual quality or fixed domain criteria, leaving open whether an appealing image is appropriate for a specific purpose, audience, cultural setting, or domain convention. We introduce AesCanvas, a unified suite with two...
-
16
Domain-Specific Self-Supervised Representation Learning for Retinal Fundus Classification
Bekzat Nurlanbekova, Fung Fung Ting
cs.CV · cs.LG
Despite the growing number of public datasets, annotated medical images remain scarce. Supervised learning methods achieve strong performance on many benchmarks, however require large amounts of labeled data, which are costly and time-consuming to obtain in the medical domain. To address this limitation, contrastive self-supervised learning (SSL) has emerged as a promising alternative for learning useful representations from unlabeled data....
-
17
PailitaoGR: Latent Think-with-Images for Generative Image Retrieval
Xiaomeng Fan, Yueran Liu, Shengyu Zhou, Chenghan Fu, Wanxian Guan, Feng Li, Chuan Yu, Jian Xu, Bo Zheng
cs.CV · cs.AI · cs.IR
Generative retrieval has demonstrated strong performance by directly generating product semantic identifiers (SIDs). Extending this paradigm to image search, however, is nontrivial because real-world query images contain diverse information, including the search target, useful auxiliary evidence, and irrelevant visual content. This requires the model to identify and focus on the search target while selectively utilizing auxiliary evidence. In...
-
18
CoGeo-GS: Concept-Driven and Geometry-Aware Multi-Object Removal in 3D Scenes
Yuanxiang Ni, Xianliang Huang, Chenhang Ma, Chen Xiao, Yuewen Ma, Ruxin Wang, Hao Zhang
cs.CV · cs.AI
Multi-object removal in 3D scenes is challenging due to severe occlusions, semantic entanglement, and the difficulty of maintaining geometric and multi-view consistency. Existing 3D Gaussian Splatting (3DGS) methods perform well for single-object editing but scale poorly to multi-object scenarios, often requiring repetitive optimization and yielding unstable geometry in removed regions. We propose CoGeo-GS, a concept-driven framework for...
-
19
Hierarchical Channel Stacking: A Structured Decision Framework for AI-Generated Image Detection
Saifullah Shoaib, Akash Borigi, Rupendra Lekkala, Amaury Lendasse, Edward Ratner, Sai Sowjanya Bhamidipati,...
cs.CV · cs.LG
Many synthetic-image detectors produce accurate predictions but offer limited insight into how those decisions are formed. This paper introduces Hierarchical Channel Stacking (HCS), a compact framework for AI-generated image detection that converts intermediate CNN activations into a structured 60-dimensional representation organized across three progressively deeper backbone stages. HCS uses per-channel Level-1 classifiers and a Level-2...
This edition is part of The Daily Abstract — cs.CV archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.