cs.CV · 2026-07-25 · No. 64
Computer Vision and Pattern Recognition, 2026-07-25.
15 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
15 entries-
01
3D-Aware VLMs with Implicit and Explicit Geometries
Wenhao Li, Xueying Jiang, Quanhao Qian, Deli Zhao, Ran Xu, Shijian Lu, Gongjie Zhang
cs.CV · cs.AI · cs.LG
Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that require fine-grained spatial understanding and reasoning. To bridge this gap, we present VLM-IE3D, a unified framework that enhances the 3D spatial awareness of VLMs by equipping them with both implicit and explicit 3D geometries learned from RGB videos. Our VLM-IE3D introduces Implicit Geometry...
-
02
GraphVid: Interactive Graph-Controllable Video Generation
Vedant Shah, Onkar Susladkar, Tushar Prakash, Kiet Nguyen, Tianjio Yu, Adheesh Juvekar, Muntasir Waheed, Ismini Lourentzou
cs.CV · cs.AI
Controllable video generation remains challenging due to the difficulty of specifying precise multi-object interactions using text prompts or motion-control inputs that primarily constrain pixel movement. In practice, trajectory-based control often requires users to draw accurate tracks for multiple objects, which scales poorly with scene complexity and becomes ambiguous under occlusion or overlap. To enable flexible yet precise multi-subject...
-
03
Synthetic data generation framework for quality control automation in gravure printing
Korota Arsène Coulibaly, Mohamed Hamlich, Khalid Hmali, Andrea Trombin
cs.CV · cs.AI · cs.LG · eess.IV
Quality control in printing, particularly in rotogravure printing, still depends on slow, costly, and subjective manual inspection. Automated surface defect detection is critical for maintaining high-quality standards in rotogravure printing. Deep learning models give prospects for automation. However, training robust deep learning models, such as YOLO or Vision Transformers, is heavily hindered by the extreme scarcity of real-world...
-
04
Visual Contrastive Self-Distillation
Yijun Liang, Yunjie Tian, Yijiang Li, Yuqi Jia, Furong Huang, Tianyi Zhou, Di Fu
cs.CV · cs.AI
On-policy self-distillation (OPSD) is promising as it removes the external teacher required by on-policy distillation (OPD), yet it still needs asymmetric information between teacher and student to ensure that the self-teacher provides a stronger learning signal than the student. Existing methods create this asymmetry either through privileged answers or visual evidence. We ask whether both can be removed, yielding a simpler form of OPSD...
-
05
ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing
Yueyi Liu, Chi Zhang, Sen Cui, Miao Liu
cs.CV · cs.AI
Test-Time Tuning (TTT) on pretrained diffusion models has emerged as a powerful paradigm for video editing. However, there exists a foundational mismatch between the distribution-mapping nature of generative models and the single-point optimization of standard TTT. In this paper, we demonstrate that this mismatch triggers \textit{Prior Collapse}, a degenerate state where the model discards the text conditions and spatial latents, collapsing...
-
06
Adaptive Identity Anchoring: Closed-Loop Keyframe Placement for Synthetic Paired Supervision in Video Face Swapping
Logan Robbins
cs.CV · cs.AI
Video face swapping has no natural paired supervision: no real footage exists of one person's face performing another person's video. The strongest current answer, DreamID-V's SyncID-Pipe, mints pairs by replacing the identity in exactly two frames of a real clip -- the first and the last -- and regenerating the rest from a pose sequence alone. Pose carries no appearance evidence of the swapped-in identity, so over long clips, occlusions, and...
-
07
When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation
Dongbin Na
cs.CV · cs.AI
A vision-language AI assistant returns its answer as a stream of generated tokens. Therefore, a safety guard that watches that answer has to keep up with the stream and stop a harmful reply before a user reads it. Recent vision-language guardrails instead generate a chain of thought before they issue a verdict. They believe that step-by-step reasoning yields a safer guard. This design makes the guard heavy and slow, since the model must...
-
08
DINOde: Continuous Vision-Text Alignment for Open-Vocabulary Semantic Segmentation
Sung-Hoon Yoon, Hoyong Kwon, Changgyoon Oh, Kuk-Jin Yoon
cs.CV · cs.AI
Open-vocabulary semantic segmentation (OVSS) leverages textual semantics to segment objects beyond predefined categories. While the self-supervised model DINOv3 provides strong structured visual representations, its lack of native textual alignment hinders its direct application to OVSS. To bridge this gap, we propose DINOde, an ODE-based framework that continuously aligns CLIP text embeddings with the DINO visual manifold. Our approach...
-
09
PC-Edit: Prompt-Contrastive Region Discovery and Region-Guided Editing
Jian Zhang, Zhijun Zhang
cs.CV · cs.AI
Replacing an object with one that differs in category or shape requires complete source removal, natural target formation unconstrained by the source silhouette, and preservation of unrelated content. Existing training-free editors either localize edits from terminal predictions under source and target prompts or preserve unrelated content through spatially unselective source-feature reuse without explicit region discovery. Before reaching...
-
10
Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning
Lorenzo Orsingher, Thomas De Min, Massimiliano Mancini, Davide Talon, Elisa Ricci
cs.CV · cs.AI
Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations. To evaluate unlearning effectiveness in multimodal large language models (MLLMs), prior works fine-tune models on fictitious identities, simulating unlearning requests on subsets of these IDs, which are typically uniformly distributed. However, in realistic scenarios, people from different demographic groups may...
-
11
DART: A Degradation-Aware Recurrent Transformer for Archival Film Restoration
Mikołaj Jastrzębski, Wojciech Kozłowski, Kamil Adamczewski
cs.CV · cs.LG
Archival film restoration is a challenging problem because historical footage contains compound degradations such as scratches, dust, blur, noise, flicker, and photometric aging, while clean reference videos are unavailable. Existing video restoration methods largely treat these degradations implicitly, reconstructing frames without explicit knowledge of where damage occurs or how severe it is. We propose DART, a degradation-aware recurrent...
-
12
CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of Knowledge-Intensive VQA
Hanseok Oh, Parishad BehnamGhader, Benno Krojer, Hyunji Lee, Paul Liang, Siva Reddy, Verna Dankers
cs.CV · cs.AI
Knowledge-Intensive Visual Question Answering (KI-VQA) benchmarks evaluate Vision-Language Models (VLMs) as multimodal knowledge assistants by requiring external information beyond a provided image to answer questions. KI-VQA involves multiple sub-problems -referring expression understanding, visual grounding, object recognition, knowledge retrieval, and reasoning-yet existing benchmarks typically report only end-task accuracy, obscuring...
-
13
Safety-oriented sidewalk and road segmentation for smartphone-based assistive navigation
Hakan Calim, Anamaria Dumitrescu, Adarsh Bhandary Panambur, Huzaifa Asif, Andreas Maier
cs.CV · cs.LG
Independent sidewalk mobility is essential for blind and visually impaired pedestrians (BVIPs), yet smartphone-based assistive navigation requires perception models that distinguish walkable sidewalks from adjacent unsafe regions. This study presents a safety-oriented semantic segmentation framework for future mobile guidance. We introduce SENSATION-DS, a chest-height pedestrian-view dataset with 2,752 image-mask pairs and nine-class...
-
14
Sparse Concept Channels in Frozen 3D CT Vision Encoders
Farhad Nooralahzadeh, Lea Bogensperger, Christian Bluethgen, Michael Krauthammer
cs.CV · cs.AI
Large vision-language models are becoming increasingly dominant in 3D medical image interpretation, but we rarely know <i>which</i> internal units encode clinical findings or <i>where</i> that information lives in the representation. We first study this on a 3D chest vision-language model (Pillar-0) by probing its frozen vision embeddings. We show that (i) each radiological finding is encoded by a <i>sparse</i> set of ~10 vision-encoder...
-
15
HyWorldVLA: A Vision-Language-Action Model with Hybrid World Modeling for Autonomous Driving
Quanfu Yu, Xian Wu, Hao Xu, Liulong Ma
cs.CV · cs.AI
Vision-Language-Action (VLA) models augmented with world modeling represent a promising paradigm for end-to-end autonomous driving. While pixel-level future prediction enables fine-grained spatiotemporal reasoning, it compromises robustness in noisy driving scenarios. Conversely, latent-based world models alleviate this sensitivity but often incur limited interpretability and representational degradation due to absent pixel-level grounding....
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.