cs.CV · 2026-10-23 · No. 151

Computer Vision and Pattern Recognition, 2026-10-23.

12 new papers in cs.CV. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

12 entries
  1. 01

    Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success

    Yunfei Xie, Howard H. Qian, Shiyi Lan, Kaiyu Hang, Chen Wei

    cs.CV · cs.LG · cs.RO

    Robotic foundation models are typically evaluated through costly closed-loop rollouts, which motivates cheap offline proxies for model capability. The Platonic Representation Hypothesis (PRH) suggests that as representations improve, different modalities such as vision and language converge toward a shared statistical model of reality. We ask whether motion trajectories form another such modality: as embodied models become more capable,...

    arxiv.org/abs/2610.31670 · PDF

  2. 02

    SpectralCanary: Embarrassingly Simple Low-Frequency Traces for T2I Dataset-Use Auditing

    Sy-Tuyen Ho, Anirudh Satheesh, Soham Chawathe, Huy Nghiem, Yongkyun Lee, Andrew Adams Schoen, Furong Huang

    cs.CV · cs.LG

    Auditing whether a text-to-image (T2I) model was fine-tuned on a particular image collection is difficult: a model can absorb collection-level visual characteristics without reproducing training images. Proactive dataset-use auditing plants a shared signal in a dataset before release, then later checks whether that signal appears in a suspect model's generated outputs. Existing approaches often trade off verifiability, fidelity, robustness,...

    arxiv.org/abs/2610.31659 · PDF

  3. 03

    Beyond Best-of-$k$: Prior-Consistent DAPS for Ambiguous Nonlinear Inverse Problems

    Merve Kocabas, Benjamin A. Burns, Andreas Geiger, Kent Gauen, Sara Fridovich-Keil

    cs.CV · cs.LG

    Diffusion models have become strong priors for solving inverse problems. However, nonlinear inverse problems such as phase retrieval remain challenging when multiple measurement-consistent solutions are distinguishable only by the prior; we call such measurements ambiguous. Existing diffusion-based samplers rely on local approximations during reconstruction. For an ambiguous measurement, these approximations can allow measurement guidance to...

    arxiv.org/abs/2610.31592 · PDF

  4. 04

    LACToS: Local Anomaly Detection via Conditional Typicality of Superpixels

    Jihoon Hong, Alireza Kheirandish, Rohan Sanda, Sara Fridovich-Keil

    cs.CV · cs.LG

    Local anomaly detection is the task of identifying spatially confined anomalous or out-of-distribution (OOD) regions within an otherwise in-distribution (ID) image. Most existing methods are designed for a specific context, with a strong focus on industrial defect detection, where they achieve excellent performance on well-established benchmarks. However, we observe that these methods can exhibit significant performance drops in other...

    arxiv.org/abs/2610.31538 · PDF

  5. 05

    MoG-VLM: Efficient Video Anomaly Detection through Motion-Guided Vision-Language Models

    Khaled Waleed Dawoud, Muhammad Zaigham Zaheer, Khan Muhammad, Muhammad Haris Khan

    cs.CV · cs.AI · cs.LG

    Vision-Language Models (VLMs) have shown strong potential for video anomaly detection, but dense frame-level inference makes them impractical for real-time deployment. Existing acceleration commonly relies on uniform sampling, which ignores content dynamics and can either waste computation on static segments or miss localized anomalies. We propose MoG-VLM a motion-adaptive anomaly detection framework that leverages motion purely as a...

    arxiv.org/abs/2610.31478 · PDF

  6. 06

    Data-Driven Vision-Language Models for Remote Sensing: A Survey

    Yue Zhou, Shujun Zhao, Xue Yang, Ruigang Li, Tianwen Zhang, Mengcheng Lan, Chaofeng Chen, Lingfei Ma, Hongjie He, Jonathan Li

    cs.CV · cs.LG

    During the deep learning era, innovations in remote sensing (RS) vision models primarily focused on optimizing network architectures for specific tasks and conducting end-to-end training. However, with the advent of the Vision-Language Models (VLMs) era, constrained by substantial computational resource demands, the mainstream research paradigm has shifted towards adapting general-purpose VLMs using RS vertical domain data for fine-tuning,...

    arxiv.org/abs/2610.31304 · PDF

  7. 07

    RecallGS: Geometry-Grounded Recall for Online Semantic Gaussian Splatting

    Thanh-Khoi Nguyen, Thien-Phuc Tran, Minh-Triet Tran

    cs.CV · cs.AI

    Online semantic 3D Gaussian Splatting (3DGS) enables open-vocabulary scene understanding from streaming observations. However, existing methods recover geometric context missing from image-derived semantic features using an additionally learned 3D network, incurring extra training and runtime overhead. We observe that such geometric-semantic evidence may already exist in the agent's observation history and can be retrieved rather than...

    arxiv.org/abs/2610.31293 · PDF

  8. 08

    RaSFNet: Ray-aligned and Scan-aware Fusion Network for LiDAR Semantic Segmentation

    Chuang Chen

    cs.CV · cs.LG

    LiDAR point cloud semantic segmentation is a fundamental component of 3D perception for autonomous driving and robotics. Projection-based methods map 3D point clouds into 2D representations for feature extraction using 2D networks. However, aggregating multiple points during projection can obscure geometric differences within each frustum, while local feature extraction limits the modeling of spatial relationships across scanning regions....

    arxiv.org/abs/2610.31186 · PDF

  9. 09

    GM-GReFEL: Geometry-Guided Spatiotemporal State-Space Learning for Robust Dynamic Facial Expression Recognition

    Yudhistira Arditya Pratama, Yi-Zeng Hsieh

    cs.CV · cs.LG

    Recognizing facial expressions in unconstrained video suffers from two coupled problems: self-attention grows quadratically in cost with clip length, and crowdsourced labels are noisy. We present GM-GReFEL, a spatiotemporal state-space network with a geometry-aware decision stage. Its Modulated GroupMamba backbone replaces a spatiotemporal Vision Transformer. Six channel groups are scanned separately, four over the frame plane and two over...

    arxiv.org/abs/2610.31140 · PDF

  10. 10

    DRAFT: Decoding and Reconstructing 3D Room Layouts from fMRI and Camera Trajectories

    Chi-Wei Lee, An-Kai Chen, Cheng-Han Chiang, Yi-Chun Chang, Po-Chih Kuo

    cs.CV · cs.LG

    While functional magnetic resonance imaging (fMRI) decoders reconstruct images and 3D objects, recovering the metric geometry of rooms from a moving viewpoint remains an open challenge. We introduce, to our knowledge for the first time, the task of reconstructing 3D layouts of held-out scenes using only the known camera trajectories and the fMRI signals of participants watching indoor walkthroughs, without any visual frames. The task is hard...

    arxiv.org/abs/2610.31108 · PDF

  11. 11

    Diagnostic Loss: Asymmetric Supervision for Radiology Report Generation

    Ignacy Kolton, Wenxuan Li, Zongwei Zhou, Jarosław B. Ćwikła, Arkadiusz Sitek, Pedro R. A. S. Bassi, Szymon Płotka

    cs.CV · cs.LG

    Automated radiology report generation requires models to do more than produce fluent clinical narratives: they must explicitly state supported diagnoses while avoiding unsupported ones. However, existing medical vision-language models (MedVLMs) are typically trained with token-level maximum likelihood objectives, which prioritize text agreement over diagnostically critical terms. As a result, models can miss key diagnoses and introduce wrong...

    arxiv.org/abs/2610.30980 · PDF

  12. 12

    Query-Time Calibration of CLIP Features for Open-Vocabulary 3D Segmentation

    Dominik Engel, Yousef Rajeh, Leon Sick, Ivan Viola

    cs.CV · cs.AI

    Lifting vision-language features such as CLIP into 3D Gaussian reconstructions enables open-vocabulary segmentation through natural-language queries. Although CLIP represents a broad range of semantic concepts, the lifted features of individual scenes can exhibit strong directional concentration, while raw cosine similarity does not account for the scene-specific feature distribution. We show that substantial segmentation gains can be...

    arxiv.org/abs/2610.30908 · PDF

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.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.