cs.CV · 2026-08-07 · No. 77
Computer Vision and Pattern Recognition, 2026-08-07.
16 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
16 entries-
01
Does FLAIR super-resolution erase or hallucinate small white-matter lesions?
Zahra Khodakarami, Yue Li, Pulkit Khandelwal, John Detre, Sandhitsu Das, Christopher Brown, David Wolk, Paul Yushkevich
cs.CV · cs.AI
White matter hyperintensities (WMH), bright regions on Fluid-attenuated Inversion Recovery (FLAIR) scans are associated with cerebrovascular pathology and neurodegeneration. FLAIR is usually acquired with thick slices in clinical settings, giving it poor through-plane resolution. Super-resolution (SR) is a widely used method for recovering an isotropic volume from an anisotropic scan. Yet whether applying it prior to WMH segmentation...
-
02
OTLesMix: Wasserstein Barycenter and Optimal Transport Map for Synthetic Lesion Generation with Diverse Shapes and Locations
Robin Trombetta, Carole Lartizien
cs.CV · cs.LG · eess.IV
The development of deep learning over the past decade has revolutionized medical imaging segmentation, allowing the extraction of precise descriptors from large volumes to characterize pathologies. Data augmentation is a technique widely regarded as a way to improve model training. It includes simple transformations like spatial operations or intensity modifications, but also more advanced synthesis techniques. Their goal is to generate new...
-
03
Toward Deployable Bangla Sign Language Recognition with Expert-Validated Data and a Lightweight Attention-Based Model
Saad Ahmed, Md Khalid Syfullaha
cs.CV · cs.AI
Deaf and hard-of-hearing people in Bangladesh communicate mainly through Bangla Sign Language (BdSL). Automatic BdSL recognition on personal devices could widen access to education and services. Existing systems use controlled-setting datasets without expert verification and heavyweight pretrained backbones unsuited to on-device use. We introduce RSBdSL38, 10,874 expert-validated images spanning all 38 BdSL hand signs, representing the 51...
-
04
PRISM: Distribution-Gated Flow Matching for Controllable Unpaired Image Translation
Elad Yoshai, Natan T. Shaked
cs.CV · cs.AI
Unpaired image-to-image translation must decide, per image, what to change and what to preserve without paired supervision. Many diffusion-based unpaired translators control preservation through a single global noise or guidance value applied across the image, which cannot separate content to keep from appearance to change. We present PRISM, a GAN-free flow-matching framework that replaces this global control with a learned per-feature gate....
-
05
Depth-Guided Video Object Counting in Crowded Scenes
Yuanjing Xu, Xinyan Liu, Weidong Chen, Zixuan Zou, Linhao Zhang, Zhuangzhe Meng, Antoni B. Chan, Weigang Zhang
cs.CV · cs.AI
Our primary objective is to advance video object counting in crowded scenes, aiming to robustly count all instances of a target category based on given text or visual prompts. Existing methods rely on RGB information, limiting their discriminative ability in crowded and occluded conditions. To address this, we propose a Depth-Guided Detector (DG-Det) along with a general post-processing pipeline. By integrating depth cues with multi-scale...
-
06
Domain-Grounded Candidate Selection for Agentic Image Editing: A Shadow Removal Case
Shilin Hu, Jingyi Xu, Dimitris Samaras, Hieu Le
cs.CV · cs.AI
Commercial vision-language models are reshaping computer vision, with visual priors broad enough to rival task-specific systems. This raises a natural question: do they reduce the need for classic, physics-informed low-level vision? We study this through shadow removal, a problem shaped by scene geometry, illumination, materials, and occluders, where paired shadow and shadow-free data are hard to collect at scale. We find that a commercial...
-
07
Big, Bright, or Invisible: A Frozen-Feature Benchmark of 3D CT Foundation Models
Maulik Chevli, Johannes Brandt, Rickmer Braren, Daniel Rueckert, Philip Müller
cs.CV · cs.AI
Routine CT interpretation is inherently comprehensive, capturing incidental findings across the entire scan volume. 3D CT foundation models could assist this process by providing generalizable representations of anatomy and pathology. To evaluate their diagnostic breadth, we benchmark ten frozen CT encoders across three cohorts of thoracic CT scans, including an unseen internal clinical dataset, using $k$-nearest neighbors, zero-shot...
-
08
MirrorNet: Can Medical Image Anonymization Really Protect Patient Identity?
Attila Simkó
cs.CV · cs.LG
Medical images are routinely de-identified---names, dates, and other metadata removed---and then shared for research, teaching, and public benchmarks under the assumption that this renders them anonymous. Such de-identification protects the metadata but not the pixels, and---apart from scans that directly contain facial structures---whether the image content itself identifies the patient has received little scrutiny. We investigate this...
-
09
D-CLOT: Double Closed Loop Optimal Transport for Unsupervised Action Segmentation
Elena Bueno-Benito, Mariella Dimiccoli
cs.CV · cs.AI
Optimal transport (OT) has emerged as an effective framework for unsupervised action segmentation. Yet, in existing OT-based methods, the latent action prototypes that define the OT costs are not re-estimated from the refined frame geometry. Instead, they evolve solely through gradients from the pseudo-label loss. We identify this \emph{representation--prototype inconsistency} as a central bottleneck, particularly around ambiguous transitions...
-
10
KVAE: Family of Tokenizers for Multimodal Generative Models
Andrey Shutkin, Denis Parkhomenko, Ivan Kirillov, Kirill Chernyshev, Kirill Malakhov, Ilia Vasiliev, Ilia Trushkin,...
cs.CV · cs.LG · cs.SD
Latent diffusion modeling (LDM), a prominent paradigm, utilizes tokenizers to map input signal to compressed representation. This dependency positions tokenizer as an integral part of generation process itself, since it affects learning speed, quality of synthesized samples and lay foundation for later applications. This report presents series of KVAE tokenizers for audio, image and video, all designed for subsequent text-conditioned...
-
11
VSMP-IMU: Video-Grounded Semantic Motion Programs for Sensor-Aware Synthetic IMU Generation
Lala Shakti Swarup Ray, Vitor Fortes Rey, Mengxi Liu, Paul Lukowicz, Bo Zhou
cs.CV · cs.LG
Wearable human activity recognition (HAR) is often limited by the scarcity of labeled sensor data, especially in low-resource, class-imbalanced, and subject-generalization settings. Synthetic IMU generation can reduce this dependency and enhance HAR machine learning model's performance, but existing approaches face a trade-off without addressing all factors: video-driven methods are visually grounded but sensitive to pose-estimation errors,...
-
12
SR-JEPA: Learning Predictive Latent State in 3D Scenes
Zihan Zhou, Qifu Wen, Xi Zeng
cs.CV · cs.LG
Joint-embedding predictive architectures learn by predicting latent representations of missing observations, yet many masked JEPAs are evaluated primarily through the encoders they produce. We ask what a trained predictive pathway itself infers when an entire entity is absent from a native 3D scene. We introduce SR-JEPA, a point-native JEPA for scene-scale point clouds whose original frozen predictive pathway can be queried at a supplied...
-
13
HyTBE: Hyperbolic Target-Background Expert Model for Cross-Domain Infrared Small Target Detection
Aohua Li, Jin Kuang, Yubing Lu, Pingping Liu
cs.CV · cs.AI
Infrared small target detection (IRSTD) has achieved substantial progress under domain-consistent evaluation, yet detector performance often degrades markedly when generalizing to unseen infrared domains. Existing methods primarily improve detection by enhancing target responses and suppressing background interference. However, when trained on only a limited set of source domains, their learned decision rules are inevitably established from a...
-
14
UniVVT: A Unified End-to-End Framework for High-Fidelity Video Virtual Try-on
Yushe Cao, Shikun Feng, Fei Shen, Haikuo Peng, Jianqiang Xia, Yiheng Zhu, Dianxi Shi, Chun Yu
cs.CV · cs.AI
Video Virtual Try-On (VVT) synthesizes a video of a person wearing a target garment while preserving identity, motion, and scene dynamics. Dominant approaches cast VVT as mask-conditioned video inpainting and rely on separate modules for human parsing, pose estimation, and garment warping. This multi-stage design complicates deployment and, more critically, allows errors in explicit geometric priors to propagate irreversibly into the...
-
15
Engram-E2VID: Reference-Based Event-to-Video Reconstruction via Generative Activation of Appearance Engrams
Feiyu Ji, Xiang Li, Hao Ma, Tianxiang Huang, Qingxin Lu, Mengqi Ji, Lei Han, Xiaokang Yang, Xiaoyun Yuan
cs.CV · cs.LG · physics.optics
Reference-based event-to-video reconstruction aims to recover target RGB frames from a reference frame and the event stream captured over the reference-to-target interval. Although events provide fine-grained temporal cues, they encode sparse and asynchronous log-intensity changes rather than absolute appearance, making faithful reconstruction intrinsically challenging. The central challenge lies in associating event-derived target-time...
-
16
DistMedVL: Distributional Vision-Language Alignment for Uncertainty-Aware Medical Image Segmentation
Jiaxuan Li, Qing Xu, Xiangjian He, Yue Li, Daokun Zhang, Fiseha B. Tesema, Rong Qu
cs.CV · cs.AI · cs.MM
Cross-modal alignment of visual and textual representations is fundamental to multimodal medical image understanding, yet remains hindered by uncertainty in both modalities under real-world clinical conditions. Existing vision-language segmentation methods rely on deterministic cross-modal matching, which overlooks aleatoric uncertainty from ambiguous boundaries and epistemic uncertainty from limited training data, leading to fragile...
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.