cs.CV · 2026-08-18 · No. 88
Computer Vision and Pattern Recognition, 2026-08-18.
26 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
26 entries-
01
Unsupervised Learning of Cell Instances with Generative Routing Pyramids
Ziwen Liu, Martin Weigert
cs.CV · cs.LG · q-bio.QM
Identifying and representing object instances such as cells or nuclei is a common task in microscopy image analysis. Established machine learning workflows typically use supervised detection or segmentation followed by feature extraction or classification, which requires manual annotations and treats instance segmentation and cell representation as separate stages. We describe a new unsupervised method for cell instance segmentation and...
-
02
Diagnosing Dense Same-Class Attribute Misbinding in Large Vision-Language Models
Yuanzhi Xu, Qian Gao, Jun Fan, Guohui Ding, Zhenyu Yang, Yuteng Xiao, Sixue Lin
cs.CV · cs.AI
Large vision-language models can recognize the objects and attributes in a crowded scene yet assign an attribute to the wrong same-class instance. Generic visual-question-answering accuracy marks the response as wrong, while object-hallucination metrics may regard both the object and attribute as image-supported; neither reveals the transfer. This study formalizes this blind spot as Dense Same-Class Attribute Misbinding (DSCAM) and presents...
-
03
Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching
Ye Lu, Shen Wang, Zhaoyang Zhang, Yihan Yan, Li Liu, Runze Liu, Fanghui Sun
cs.CV · cs.AI · cs.CR · cs.MM
Model Inversion Attacks (MIAs) aim to reconstruct representative training samples of target identities from face recognition models, exposing critical security vulnerabilities. Existing methods typically rely on indirect guidance or highly stochastic guidance, making it difficult to stably optimize generation trajectories toward target facial images. In this paper, we propose Steering Flow Model Inversion (SFMI), a novel two-stage white-box...
-
04
TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation
Haoran Wang, Chaofan Ma, Ran Yi, Lizhuang Ma
cs.CV · cs.AI
Despite recent advances in unified multimodal models for multi-reference image generation, existing benchmarks remain organized around predefined task types (e.g., "subject composition"), which are ill-suited to this combinatorial setting and lead to fragmented coverage, uncontrolled complexity, and little diagnostic value. Recognizing that diverse multi-reference tasks share a common set of atomic operations, we adopt a capability-oriented...
-
05
Unsupervised Anomaly Detection for Image Dataset Quality Assurance in Multi-Center Breast MRI
Chiara Tappermann, Steffen Renisch, Lars Ole Schwen, Hans Meine, Horst K. Hahn, Eike Petersen
cs.CV · cs.AI
Corrupted, inconsistent, or anomalous data silently threatens the safety and reliability of medical AI. Despite growing regulatory recognition of dataset quality assurance (QA) for high-risk medical AI, scalable automated detection remains underdeveloped. We employ unsupervised anomaly detection (AD) and out-of-distribution (OOD) detection as an automated dataset QA mechanism for multi-center dynamic contrast-enhanced breast MRI. We build a...
-
06
MIRROR: Multimodal Intelligent Radiology Reasoning and Observation Reporter
Vignesh Nagarajan, Sriram Venkatapathy
cs.CV · cs.AI · cs.LG
A radiologist reading a model's output faces two problems. The model returns a number and no reason, and any system that turns that number into readable prose can quietly add claims the model never made. MIRROR is a research prototype built to separate those failures. It chains a multi-label classifier, a Grad-CAM localizer that turns each positive finding into a named anatomical region, and a report writer that receives the labels,...
-
07
Bridging the Gap between Labeled and Unlabeled Data via Unified Flow with Feature Memory Bank
Shanwen Wang, Xin Sun, Danfeng Hong, Junyu Dong, Patrick Le Callet
cs.CV · cs.AI
Although semi-supervised semantic segmentation ($\text{S}^4$) utilizes abundant unlabeled data to reduce manual labeling burdens, independent training of labeled and unlabeled data causes the former to dominate, which severely degrades pseudo-label quality. To address this challenges, we propose a novel remote sensing (RS) $\text{S}^4$ method via unified flow with feature memory bank (UFFM). Specifically, UFFM comprises two key innovations:...
-
08
Turning spectra into images improves plant trait retrieval with 2D-CNNs
Javier Lopatin, Teja Kattenborn, Eya Cherif, Sebastián Moreno
cs.CV · cs.LG
Hyperspectral reflectance spectroscopy enables non-destructive estimation of plant functional traits, yet current deep learning approaches process spectra as one-dimensional sequences, which limits how they capture long-range inter-band dependencies. We asked whether transforming 1D spectra into 2D image representations improves multi-trait prediction with convolutional neural networks (CNN). We compared nine transformations using...
-
09
X$^2$Localizer: Cross-grained Alignment for Progressive Cross-view Video Geo-localization
Zichao Zeng, Weijia Fan, Yufan Chen, June Moh Goo, Junwei Zheng, Ruiping Liu, Kunyu Peng, Jiaming Zhang, Rainer...
cs.CV · cs.AI · cs.RO
Cross-view Video Geo-localization (CVG) aims to localize ground-view videos by retrieving their corresponding geo-tagged aerial images. However, CVG approaches rely on fixed-length inputs and post-hoc refinement, hindering online-oriented localization under partial or dynamic observations. In this work, we formulate Progressive Cross-view Video Geo-localization (PCVG) as a deployment-oriented extension and evaluation protocol of CVG, enabling...
-
10
HarmTrace: Anchor-Calibrated Decoupled Optimization for Fine-Grained Target Identification in Harmful Memes
Yujia Li, Yiqun Zhang, Zihan Cheng, Yijie Huang, Tenglong Ye, Zihan Wang, Xiaocui Yang, Shi Feng, Yifei Zhang, Daling Wang
cs.CV · cs.AI
Multimodal harmful meme detection is typically formulated as image--text harmfulness classification. A model may correctly predict harmfulness while misidentifying the attacked target or its supporting evidence. We therefore extend harmful meme detection with fine-grained target identification, asking what type of target is attacked, who is targeted, and where the target appears in the meme. The model predicts harmfulness for every meme and,...
-
11
Supervising the Path to Fine Scales: GalerkinFlow for Scientific-Field and Image Super-Resolution
Zikang Zhan
cs.CV · cs.CE · cs.LG
Most super-resolution models learn from paired data by supervising only the final high-resolution output. This provides little control over how the prediction should evolve between the downsampled observation and its fine target. We introduce GalerkinFlow, an equation-agnostic framework that turns each coarse--fine pair into supervision along an entire reconstruction path. At a random sample of intermediate states on the reconstruction path,...
-
12
Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans
Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani, Ulas Bagci, Alessandro Bruno
cs.CV · cs.AI · cs.CL · cs.HC · cs.MM
Human visual search is serial: the fovea must land on a candidate to confirm it, and those landings form a scanpath. Whether multimodal large language models (MLLMs), given the same foveated input, search as humans do bears on their use as models of human vision and on attention-alignment scores. We compare three general-purpose MLLMs with human eye-movement scanpaths on goal-directed search (COCO-Search18), driving each model fixation by...
-
13
MLLM-Guided Semantic Correction for Text-to-Video Generation
Junhao Chen, Zheqi Lv, Keting Yin, Shengyu Zhang, Zhou Zhao, Feiyang Chen, Xinyu Duan, Baoxing Huai, Fei Wu
cs.CV · cs.AI
Recent advances in diffusion models and Transformer architectures have led to significant progress in text-to-video generation. However, these models often suffer from semantic errors such as missing objects, incorrect attributes, or mismatched actions. Although some semantic correction methods perform optimization before sampling or refinement after sampling, how to detect and correct semantic deviations during the video generation process...
-
14
RISE: Roadside Infrastructure Sequence Understanding across 3D Tracking and Structured Vision-Language Reasoning
Yanbo Jiang, Haotian Zheng, Jiahao Wang, Hanxiao Ren, Yitao Xu, Yining Xing, Zehong Ke, Hao Cheng, Yiqian Tu, Jinhao...
cs.CV · cs.AI
We present RISE (Roadside Infrastructure Sequence Understanding and Evaluation), a framework spanning metric 3D tracking and structured vision-language reasoning in roadside sequences. For metric tracking, our image-only method combines SAM3 video identities with calibration-guided mask agreement for multi-view identity association, recovering persistent 3D tracks without LiDAR or task-specific 3D training. Its calibration-conditioned...
-
15
Contrastive Energy Fields for Inference-Time Procedure Planning in Instructional Videos
Mohamed Afham, Christoph Reich, Oliver Hahn, Daniel Cremers, Stefan Roth
cs.CV · cs.AI
Procedure planning seeks to estimate a sequence of actions to transition from an observed initial state to a given goal state. Current procedure planning approaches directly predict action sequences from latent representations using feed-forward neural networks or diffusion-based inference. These paradigms treat every action as plausible, lacking the ability to enforce task-specific logical constraints that render certain actions irrelevant...
-
16
Self-Routed Tensor Adapters for Parameter-Efficient Universal Visual Adaptation
Suraj Yadav
cs.CV · cs.LG
Universal visual representations require adaptation mechanisms that adapt across heterogeneous domains without fragmenting knowledge into domain-specific modules. Parameter-efficient fine-tuning adapts frozen visual foundation models efficiently, but standard low-rank adapters use a fixed subspace for all inputs, which can be restrictive when domains differ in style, background, and semantic context. MoE-based adapters improve specialization...
-
17
Synthetic Data Augmentation for Satellite-Based Analysis of Battle-Damaged Agricultural Fields in Ukraine
Marta Sumyk, Oleksandr Kosovan, Iryna Voitsitska
cs.CV · cs.AI
Monitoring war-induced damage to agricultural land in Ukraine is important for understanding threats to food security, environmental stability, and post-war recovery. However, the development of computer-vision systems for satellite-based damage analysis is limited by the scarcity of labeled imagery, especially for damaged agricultural fields. This work investigates synthetic data augmentation as a method for improving classification under...
-
18
Adaptive Post-Processing Drives Instance-Level Detection in Stroke Lesion Segmentation
Qinghui Liu, Jon André Ottesen, Atle Bjørnerud, Kyrre Eeg Emblem
cs.CV · cs.AI
Instance-level lesion detection has been an increasingly larger focal point in medical image segmentation besides the more standard voxel-level overlap. Still, most pipelines are trained and post-processed for voxel overlap alone. In particular, the mismatch is most pronounced for small lesions, where a near-miss prediction---substantial overlap that falls just short of the instance-matching threshold---scores the same as a complete miss. In...
-
19
SIGMA-Lane: Scale-pyramId Gated MAmba for Temporally Consistent Video Lane Detection
Tiancheng Zhang, Mengmeng Wang, Yan Gao, Xiangjie Kong, Guojiang Shen, Jiaxin Du
cs.CV · cs.AI
Video lane detection requires predictions that remain stable across frames, yet severe vehicle occlusions can break temporal cues. In streaming recurrent models, corrupted observations may enter the hidden state and produce errors that persist into later frames. Existing occlusion-aware refinements usually provide obstacle masks as auxiliary inputs, so the state-update path is only indirectly protected. We propose SIGMA-Lane, which treats...
-
20
LaGSplat: Inferring Physics-Governed Interactive Simulation from Monocular Video Using Latent Lagrangian Gaussian Splatting
Louen Pottier
cs.CV · cs.LG
We present LaGSplat (Latent Lagrangian Gaussian Splatting), a framework that infers interactive, physics-governed dynamics from one or a few monocular videos. At inference it lets a user push on the filmed object, rigid or deformable, with an external force that was never measured, annotated, or seen during training. This is possible because a low-dimensional latent state $\mathbf{q} \in \mathbb{R}^d$ plays two roles at once: it is the...
-
21
Deep Thought Alignment: Trajectory-Level Latent Distillation for Video Reasoning
Ao Shen, Yongheng Zhang, Yinghui Li, Manning Wang, Di Yin, Xing Sun
cs.CV · cs.AI · cs.CL
Large Multimodal Models (LMMs) for video reasoning have long been hindered by the high computational cost of processing vast amounts of visual information. This dilemma motivates the transfer of the reasoning capabilities of large models to smaller, more efficient ones. On-Policy Distillation (OPD) offers a promising solution by matching output-token distributions along student-generated trajectories. However, video reasoning often depends on...
-
22
Audio-Visual Segmentation via Depth-Guided Collaborative Modeling
Zhaojin Fu, Yuyang Hong, Qi Yang, Zili Wang, Kun Ding, Shiming Xiang, Bin Fan
cs.CV · cs.AI
Audio-Visual Segmentation (AVS) is a fundamental task in multimodal perception that performs pixel-level segmentation of sounding objects in videos by leveraging both visual and audio cues. It has broad applications in video understanding, human-computer interaction, and autonomous driving. However, most existing AVS methods do not explicitly model geometric cues such as relative distance and occlusion, thereby limiting the robustness of...
-
23
CoM$^3$eT: A foundation model for medical image analysis through federated, multidimensional context integration
J. Raphael Schäfer, Kai Geissler, Till Nicke, Chiara Tappermann, Karoline Heber, Eike Petersen, Habib Mergan, Lars...
cs.CV · cs.LG
Medical foundation models improve generalization when training AI models with limited labeled data, but remain confined to a single specialty, such as pathology or radiology, and to either sparse or dense outputs, such as classification or segmentation. Here, we present CoM$^3$eT (Co-representation Multidimensional Multitask Medical Transformer), a medical vision foundation model that unifies pathology and radiology, sparse and dense...
-
24
Defake-o3: From Speculative Rationales to Verifiable Evidence for Explainable AIGI Detection
Bowen Deng, Jiahui Zhan, Yikun Ji, Haozhen Yan, Jianfu Zhang
cs.CV · cs.AI
The rapid progress of image generation models calls for AI-generated image (AIGI) detectors that are not only accurate but also explainable and reliable. While MLLM-based detectors can provide natural language explanations, existing methods often generate speculative rationales: they rely on vague or hallucinated artifacts, miss subtle localized flaws from the latest generators, and fail to provide evidence that can be visually verified. We...
-
25
Convolution-Free Holistic Multivariance Decomposition Layer for Efficient Hyperspectral Image Classification Tensor Networks
Süha Tuna, Ülker Başar
cs.CV · cs.LG · math.OC
Feature extraction for hyperspectral image classification is conventionally addressed using rigid tensor decompositions that fail to capture complex spatio-spectral interdependencies, or heavily parameterized convolutional neural networks that are computationally expensive. To overcome these limitations, this work introduces the Holistic Multivariance Decomposition (HMD) framework as a novel, end-to-end differentiable neural network layer. By...
-
26
Picking the Right Image to Classify: Reliable-Input Selection in Teledermatology
Fabian Gröger, Marco Weishaupt, Philippe Gottfrois, Simone Lionetti, Linda Wermelinger, Nipun Ranasekara, Ludovic...
cs.CV · cs.AI
Dermatology models face distribution shifts in teledermatology settings, where submitted images differ from the training data in lighting, angle, distance, focus, and framing. These test-time images are ordinary clinical photographs, but some fall outside the model's training conditions, leading the model to often misclassify them due to shifts in acquisition between training and deployment. When multiple images of the same case exist...
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.