cs.CV · 2026-06-28 · No. 37
Computer Vision and Pattern Recognition, 2026-06-28.
20 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
20 entries-
01
DanceOPD: On-Policy Generative Field Distillation
Wei Zhou, Xiongwei Zhu, Zelin Xu, Bo Dong, Lixue Gong, Yongyuan Liang, Meng Chu, Leigang Qu, Lingdong Kong, Wei Liu,...
cs.CV · cs.CL · cs.LG
Modern image generation demands a single model that unifies diverse capabilities, including text-to-image (T2I), local editing, and global editing. However, these capabilities are rarely naturally aligned and often conflict. For instance, editing tends to degrade T2I performance, while global and local editing interfere with each other. Consequently, effectively composing these capabilities has become a central challenge for image generation...
-
02
Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
Yunqi Xue, Zhijiang Li, Philip Torr, Jindong Gu
cs.CV · cs.AI
Unlike diffusion-based models that operate in continuous latent spaces, autoregressive unified multimodal models produce images by sequentially predicting discretized visual tokens. These tokens are derived from a codebook that maps embeddings to quantized visual patterns. The language-like architecture enables unified multimodal models to effectively capture text conditional information for generation, making them promising for text-to-image...
-
03
On-board Remote-Sensing Foundation Models for Unsupervised Change Detection of Disaster Events
S. Ramírez-Gallego
cs.CV · cs.AI
Remote Sensing Foundation Models (RSFMs) have emerged as a powerful alternative to supervised models for Earth Observation, allowing satellites to autonomously trigger high-resolution captures or adjust tasking parameters upon detecting an anomaly, thereby maximizing the utility of the mission's limited power and computational resources. RSFMs are versatile, unified encoders that optimize onboard storage for multiple orbital applications...
-
04
Event-Aware Instructed Assistant for Referring Video Segmentation
Jinyu Liu, Henghui Ding, Shuting He, Yu-Gang Jiang
cs.CV · cs.AI
Existing referring video segmentation methods often treat a video as a single event consisting of multiple images, overlooking the fact that a video typically contains multiple distinct events. Under such a mechanism, the model needs to directly understand all the complex content in the video and text, which can easily lead to confusion and hallucinations. To address this issue, we propose to decompose a video to a set of simple events by...
-
05
Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning
Jiahe Chen, Qian Shao, Qiyuan Chen, Jiaying He, Jintai Chen, Jian Wu, Hongxia Xu
cs.CV · cs.LG
Open-set semi-supervised learning aims to leverage unlabeled data that may contain out-of-distribution outliers while maintaining performance on in-distribution classes. Existing methods mainly follow two paradigms: filtering suspicious samples or incorporating unlabeled objectives with soft weighting. We argue that both face a common trade-off: aggressive filtering can discard informative but hard ID samples, whereas utilization can...
-
06
Scaling Multi-Reference Image Generation with Dynamic Reward Optimization
Wenwang Huang, Yusen Fu, Junjie Wang, Mengfei Huang, Yulin Li, Gan Liu, Jing Cai, Yancheng He, Zhuotao Tian
cs.CV · cs.AI
While personalized image generation has achieved remarkable progress, multi-reference image generation (MRIG) remains a challenging task. Most existing benchmarks fail to adequately evaluate complex MRIG scenarios, hindering further progress in this area. To better assess model performance on complex MRIG tasks, we introduce OmniRef-Bench, a benchmark that covers complex combinations of reference image types and a large number of reference...
-
07
Confidence-Aware Tool Orchestration for Robust Video Understanding
Yangfan He, Yujin Choi, Jaehong Yoon
cs.CV · cs.AI
Video reasoning language models implicitly assume that every input frame is equally reliable. This leads to what we term the Blind Trust Problem: under realistic perturbations such as motion blur, glare, or occlusion, frontier video reasoning models can suffer 15-30%p accuracy drops on real-world embodied benchmarks, while remaining unaware that their visual evidence has been degraded. To address this challenge, we propose Robust-TO, an...
-
08
Tractography-Driven Synthetic Data Generation for Fiber Bundle Segmentation in Tracer Histology
Kyriaki-Margarita Bintsi, Sparsh Makharia, Yaël Balbastre, Joselyn Romero Avila, Julia F. Lehman, Suzanne N. Haber,...
cs.CV · cs.LG
Diffusion MRI (dMRI) tractography enables non-invasive reconstruction of white-matter pathways, but its accuracy is fundamentally limited by indirect, low-resolution measurements of axonal organization. Tracer injection studies in non-human primates provide a gold standard for validating dMRI tractography. This, however, requires time-consuming manual annotation of fiber bundles in histology sections. We propose a synthetic-data augmented...
-
09
Bridging Vision and Language Concepts through Optimal Transport Semantic Flow
Chenyang Zhang, Anqi Dong, Guangming Zhu, Nuoye Xiong, Siyuan Wang, Lin Mei, Liang Zhang
cs.CV · cs.AI
Concept Bottleneck Models (CBMs) promise transparent reasoning by predicting through human-interpretable concepts, yet their effectiveness fundamentally depends on how well visual and textual representations are aligned or matched. Existing vision-language CBMs often rely on pre-aligned encoders or global cosine similarity, which obscures fine-grained concept localization and fails to reflect true semantic geometry. In this work, we rethink...
-
10
NaviCache: Test-Time Self-Calibration Caching for Video Generation
Zheqi Lv, Zhibo Zhu, Jinke Wang, Qi Tian, Shengyu Zhang, Zhengyu Chen, Chengxi Zang, Zhou Zhao, Fei Wu
cs.CV · cs.AI · cs.MM
Video Diffusion Models (VDMs) is constrained by immense computational costs. While offline calibration-based acceleration suffers from calibration data dependency, prohibitive calibration duration, and susceptibility to distribution shifts, offline calibration-free methods eliminate these hurdles. However, since they rely on instantaneous zero-order approximations where the mapping between input and output differences varies in real-time,...
-
11
ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP
Sicheng Zhang, Muzammal Naseer, Binzhu Xie, Naufal Suryanto, Shi Qiu, Jamal Bentahar, Naveed Akhtar, Mubarak Shah
cs.CV · cs.AI
CLIP and its variants are widely adopted visual backbones in multimodal systems, but their pretraining remains dominated by descriptive image-text alignment. As downstream applications increasingly demand visually grounded commonsense inference and compositional reasoning, it remains unclear whether CLIP-style encoders can support such reasoning without architectural changes. To address this, we present ReasonCLIP-58M, a continual pretraining...
-
12
LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration
Xuyue Huang, Zhe Chen, Wang Shen, Xiao-Ping Zhang
cs.CV · cs.LG
Diffusion Transformers (DiTs) have driven substantial progress in image and video generation but suffer from prohibitive computational costs. Feature caching accelerates inference by reusing intermediate representations. Existing methods rely on historical features for implementation simplicity, yet suffer from severe error accumulation at high acceleration ratios. To address this limitation, we investigate the nature of the requisite feature...
-
13
Anatomy-Guided Residual Motion Diffusion for Controllable 4D Cardiac MRI Synthesis
Yiheng Cao, Gustavo Andrade-Miranda, Jiatian Zhang, Lingxiao Zhao, Xin Gao
cs.CV · cs.AI
Developing robust artificial intelligence models for 4D (3D + time) medical imaging is constrained by limited annotated data, inter-device domain shifts, and privacy restrictions. To address this, we propose a 4D controllable generative framework for anatomically consistent data augmentation. A semi-supervised variational autoencoder learns a compact latent representation of anatomical volumes while jointly predicting aligned segmentation...
-
14
ProtoKV: Streaming Video Understanding under Delayed Query with Summary-State Memory
Le Tu Ngoc Minh, Jinyeong Lim, Dongsu Han
cs.CV · cs.LG
Streaming video understanding (SVU) must answer queries that arrive asynchronously while visual tokens stream continuously under strict GPU-memory and query-time latency budgets. A key challenge is delayed query: decisive cues may appear briefly, yet many subsequent updates occur before the query arrives, increasing the risk that those cues are evicted or diluted under bounded memory. We propose ProtoKV, a constant-footprint SVU memory that...
-
15
Robust Onion: Peeling Open Vocab Object Detectors Under Noise
Priyank Pathak, Mukilan Karuppasamy, Aaditya Baranwal, Shruti Vyas, Yogesh S Rawat
cs.CV · cs.AI
The impact of real-world noise on Open Vocabulary Object Detectors (OV-ODs) remains poorly understood due to their architectural complexity. We present our comprehensive analysis Robust Onion, an empirical study that uses controlled synthetic visual degradations to peel OV-ODs layer-by-layer, revealing how, why, and where robustness degrades, systematically analyzing feature collapse. Our findings reveal that models with similar vision...
-
16
Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customization
Xuancheng Xu, Gengyun Jia, Bing-Kun Bao
cs.CV · cs.AI
Video customization based on Text-to-Video (T2V) models aims to learn specific features from reference data to generate controllable videos. While significant strides have been made in image stylization and video motion customization, simultaneously controlling multiple concepts, such as content, style, and motion, remains a major challenge. In this work, we systematically define the task of multi-concept video customization, which requires...
-
17
FracEvent: Event-Camera Simulation via Fractional-Relaxation Pixel Dynamics
Langyi Chen, Chuanzhi Xu, Haoxian Zhou, Pengfei Ye, Ziyu Luo, Haodong Chen, Qiang Qu, Xiaoming Chen, Weidong Cai
cs.CV · cs.LG · eess.IV
Event cameras asynchronously report brightness changes with microsecond-level temporal resolution, but real event data remain difficult to collect at scale because specialized sensors, careful synchronization, and task-specific annotations are required. Event-camera simulation is therefore important to event-based vision tasks. Most practical simulators build on contrast-threshold event generation, some with additional filtering, stochastic...
-
18
SpaceRipple: Lightweight Semantic Delivery for Mission-Oriented LEO Earth Observation Satellite Networks
Ziyi Yang, Hao Yuan, Yunxiang Yi, Wenbo Wang, Xing Zhang
cs.CV · cs.AI · cs.GR
Earth observation satellite networks generate massive volumes of high-resolution imagery, whereas inter-satellite and downlink resources remain limited. In many time-sensitive missions, ground users require mission-relevant semantic information rather than a full raw-image downlink. This paper proposes SpaceRipple, a lightweight framework for mission-oriented semantic delivery and on-board processing in Earth observation satellite networks. A...
-
19
Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection
Yangjun Wu, Keyu Yan, Yu Liu, Jingren Zhou, Fei Huang, Rong Zhang, Zhou Zhao, Fei Wu
cs.CV · cs.AI
The rapid advancement of generative models presents a significant challenge to existing deepfake detection methods, particularly given the widespread dissemination of highly realistic AI-generated images. Although Multimodal Large Language Models (MLLMs) show strong potential for this task, existing approaches suffer from two key limitations: insufficient sensitivity to fine-grained forensic artifacts and reliance on static synthetic...
-
20
From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP
Zhixing Li, Yinan Yu
cs.CV · cs.AI
Current VLM evaluations often conflate language priors with genuine spatial reasoning. To address this, we introduce CRISP, a novel structural-diagnostic evaluation paradigm that assesses visual spatial intelligence through consistency, the alignment between implicit perception and explicit reasoning. Unlike traditional black-box QA, CRISP utilizes metric 3D Scene Graphs and an oracle intervention protocol to decouple latent reasoning...
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.