cs.CV · 2026-08-10 · No. 80
Computer Vision and Pattern Recognition, 2026-08-10.
17 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
17 entries-
01
MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation
Youjun Zhao, Alex Warren, Gary K. L. Tam, Rynson W. H. Lau
cs.CV · cs.LG
Recent advances in video diffusion models (VDMs) have enabled high-fidelity video synthesis. However, generating mirror reflections remains challenging because the content within a mirror must remain consistent with the surrounding scene. Existing VDMs are not specifically designed to model scene-to-mirror relationships, which can lead to reflections with incorrect content or inconsistent spatial arrangements. We observe that mirror...
-
02
SABRE: Scalable and Automated Benchmarking of VLMs under Stress
Zixuan Lan, Luzhe Sun, Matthew R. Walter, Jiawei Zhou
cs.CV · cs.AI · cs.CL
Vision-language models (VLMs) are improving rapidly, but benchmark development lags behind, making weaknesses hard to identify. Building stress tests is costly: samples must satisfy controlled conditions, remain answerable, and challenge current models. We present SABRE, a scalable, automated pipeline that converts a Test Primer (a Markdown Task Design with Data Schema) into structured specifications, generated or edited images, and...
-
03
I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning
Shibo Gao, Chongxiao Wang, Chenglong Huang, Jie Ma, Haolin Shi, Fei Ding, Jing Li, Qiang Lyu, Yangyang Liu, Yang...
cs.CV · cs.AI
Real-world video reasoning often involves multimodal, multi-source inputs, whereas existing video reasoning tasks typically assume a simplified video-text setting, limiting identity matching and person-centric reasoning. To bridge this gap, we introduce the Identity-conditioned Queries (ICQ) task, in which models are required to jointly associate and interpret an input video and a reference image of a person, and leverage this conditioning to...
-
04
Addressable Memory for Video World Models
Xindi Wu, Sven Elflein, James Lucas, Olga Russakovsky, Laura Leal-Taixé, Despoina Paschalidou, Jonathan Lorraine, Aljoša Ošep
cs.CV · cs.LG
We study visual persistence in interactive video world models. These models rely on a Key-Value (KV) cache as a growing visual memory to carry forward previously generated frames. However, we find that models can no longer reliably address stored content once rollouts extend beyond the training horizon, because temporal Rotary Positional Embeddings (RoPE) offsets then fall outside the range seen during training and the model struggles to...
-
05
GeoDistill-Refine: Silhouette-First Geometry Distillation for Annotation-Free Spacecraft Segmentation
Yonglong Zhang, Zongwu Xie, Yang Liu
cs.CV · cs.AI
Foundation segmentation models can provide supervision for spacecraft imagery without manual training masks, but their predictions vary with textual prompts and may contain geometric errors that are amplified during distillation. This paper presents GeoDistill-Refine, a two-stage framework that transfers offline SAM 3 pseudo-masks to a compact segmentation network. Six fixed prompts are fused by an unweighted 50% vote to stabilize the teacher...
-
06
H2AL: Hyperbolic Hierarchy-aware Aggregative Learning for Registration-based Few-shot Medical Image Segmentation
Jia Wang, Jiaming Cai, Zunying Hu, Zhanjie Wu, Jinyuan Liu, Hua Cheng, Yun Peng
cs.CV · cs.AI
Registration-based Few-shot medical image segmentation (RFMIS) aims to generate pseudo-labels for unlabeled images by warping a labeled image through registration. However, existing methods primarily perform pixel-level optimization and inference in Euclidean space, treating anatomical structures as flat and disjoint. This neglect of inherent hierarchies degrades pseudo-label quality and weakens the discrimination of ambiguous regions,...
-
07
Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination
Zichuan Wang, Songlin Yang, Bo Peng, Zhenchen Tang, Yang Li, Beibei Dong, Jing Dong
cs.CV · cs.AI
Large Vision-Language Models (LVLMs) often suffer from object hallucination, generating objects that are absent from the image. Prior work largely attributes this to insufficient visual attention. However, we find that both real and hallucinated objects receive equally strong visual attention in the model's mid-to-late layers, suggesting that the key issue may not be how much the model attends, but what it attends to and why. To this end, we...
-
08
EliSeg: Verified Target Construction for Report-Grounded Abnormality Segmentation
Chengyi Peng, Haoyu Yang, Meixing Shi, Yuxiang Cai, Yankai Jiang
cs.CV · cs.AI
Radiology reports describe clinical observations but do not specify executable segmentation targets. They may contain present, negated, prior,uncertain, or irrelevant findings, while multiple valid abnormalities may coexist. Existing segmentation methods largely bypass this ambiguity by receiving a target identity or spatial prompt before inference, which acts as a hidden target oracle. We study report-grounded abnormality segmentation, where...
-
09
Representation-driven Endoscopic Visual Embedding Alignment for Latent Generation
Francisco Caetano, Tim J. M. Jaspers, Haiko Middeljans, Martijn R. Jong, Rixta A. H. van Eijck van Heslinga, Floor...
cs.CV · cs.AI
Developing foundation generative models for endoscopy is limited by the gap between natural and clinical images and the computational cost of training large Diffusion Transformers. Although representation alignment has improved efficiency in general computer vision, its role within the highly specialized endoscopic image space remains unclear. We introduce REVEAL (Representation-driven Endoscopic Visual Embedding Alignment), the largest...
-
10
Geometry-Aware Camera Localization for Bronchoscopy
Lumin Chen, Qingyao Tian, Jinpeng Li, Haoyu Jiang, Huai Liao, Xinyan Huang, Hongbin Liu, Dong Yi
cs.CV · cs.AI
Camera localization in bronchoscopy remains a challenging problem due to stringent accuracy requirements, real-time constraints, and limited training data. Compared to natural scenes, the confined anatomical structures demand millimeter-level precision, while intraoperative guidance necessitates low-latency inference. However, existing methods often fail to effectively exploit preoperative geometric priors, limiting their robustness and...
-
11
International Transfer of Stochastic Cortical Self-Reconstruction
Fabian Bongratz, Zhizheng Zhuo, Chao Zhang, Yaou Liu, Dennis M. Hedderich, Christian Wachinger
cs.CV · cs.AI · cs.LG · q-bio.NC
Stochastic cortical self-reconstruction (SCSR) enables personalized mapping of gray matter atrophy, a hallmark of neurodegenerative disorders such as Alzheimer's disease (AD), onto high-resolution cortical surfaces. Unlike conventional normative modeling approaches, which typically operate at a coarse regional level and remain inherently constrained by the covariates included during training, SCSR estimates an individualized healthy reference...
-
12
RoRA: Role-Oriented Regional Allocation for Visual Token Pruning in MLLMs
Qiyanhui Lu, Han Wu, Rongjian Xu, Tingzhang Luo, Cheng Fan, Xinghao Chen, Minjing Dong, Jufeng Yang, Jianyuan Guo
cs.CV · cs.AI
Multimodal large language models (MLLMs) encode images as long visual token sequences, making prefilling and KV-cache storage expensive. Existing training-free pruning methods select tokens by importance, diversity, or spatial coverage, but treat retained tokens as interchangeable and do not explicitly track which object-related regions are already covered. We present RoRA, a training-free framework that casts visual token pruning as...
-
13
Debias in Text, Believe Your Eyes: Text-Anchored Cross-Modal Transfer for Visual Counter-Commonsense Reasoning
Chen Ling, Hanqian Li, Dongnan Liu, Keyu Qian, Jungang Li, Xinglong liu, Shiyi Wang, Xin Dong, Pengcheng Zhu, Wei...
cs.CV · cs.AI
The visual reasoning ability of multimodal large language models (MLLMs) is crucial for downstream applications, particularly counter-commonsense reasoning, which requires models to reason beyond common assumptions. Recent studies mainly improve visual counter-commonsense reasoning by enhancing visual inputs, following the assumption that failures originate from insufficient visual grounding. However, our empirical analysis reveals that the...
-
14
MaskFlow: Precise, Consistent and Seamless Regional Image Editing
Rui Xu, Yang Yong, Shunzi Yang, Ruihao Gong, Chengtao Lv
cs.CV · cs.AI
Regional image editing has attracted considerable attention for its spatial controllability. Although instruction-based and mask-reference-based editing methods can achieve strong semantic alignment, reliable regional control remains challenging, where an edit must be accurately localized and naturally integrated with the preserved context. We propose \textbf{MaskFlow}, a training framework for precise localization, consistent background...
-
15
Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models
Minseok Kang, Hyunwoo Kim, Chanyoung Kim, Minwoo Kim, Jaekoo Lee, Dahuin Jung
cs.CV · cs.LG
Vision-language models (VLMs) have achieved remarkable generalization across diverse multimodal tasks through large-scale pre-training, yet their rapidly increasing computational and memory requirements pose significant challenges for deployment in constrained environments. Existing pruning strategies often depend on task-specific criteria or LLM-oriented importance measures, making them unsuitable for task-agnostic pruning, where no...
-
16
FedVAR: Prototype-Aligned Federated Framework for Video Anomaly Recognition
Ghani Haider, Majid Kundroo, Boyun Eom, Dong Hwan Park, Chen Chen, Taehong Kim
cs.CV · cs.AI · cs.DC · cs.LG
In the era of Industrial Internet of Things (IIoT) and Cyber-Physical Systems (CPS), Federated Learning (FL) offers a promising decentralized intelligence paradigm for Video Anomaly Recognition (VAR). This task is vital for maintaining high-fidelity Digital Twins and ensuring safety in mission-critical environments. However, the inherent data heterogeneity across distributed edge clients leads to a fundamental challenge known as semantic...
-
17
Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection
Xuechao Zou, Shun Zhang, Kai Li, Yi Zhou, Xinyu Sun, Yuhui Chen, Zhe Wu, Congyan Lang, Junliang Xing
cs.CV · cs.AI · cs.MA
The malicious use of generative artificial intelligence to create highly realistic deepfake videos raises serious ethical concerns and poses substantial challenges to AI safety. However, existing deepfake video benchmarks provide limited coverage of recent synthesis methods and generally lack reliable fine-grained textual annotations. Meanwhile, conventional detectors and multimodal large language models (MLLMs), whether operating as a single...
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.