cs.CV · 2026-11-03 · No. 162

Computer Vision and Pattern Recognition, 2026-11-03.

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
  1. 01

    Structured Visual Landscape: Generating Preferred Representations in Biological and Artificial Neural Networks

    Yusong Zhao, Edgar Y. Walker, Hao Wang, Mi Lu

    cs.CV · cs.LG · cs.NE

    Understanding how neurons respond to visual stimulus is an important question in both deep learning and neuroscience. It has significant implications for enhancing the interpretability of black-box artificial neural networks and for understanding the visual representation in the human brain. We propose a structured visual representations landscape and design an activation-based prior that allows us to effectively regularize the landscape with...

    arxiv.org/abs/2611.03597 · PDF

  2. 02

    PlantVLM-Edge: Quantized Vision-Language Models for On-Device Crop Health Diagnosis

    Gaurab Wagle, Bishal Adhikari, Jiajia Li, Xiaolei Huang, Dong Chen

    cs.CV · cs.AI

    Timely and accurate crop health diagnosis is essential for sustainable agricultural production, yet accurate diagnosis often requires expert knowledge that is not readily available. Recent vision-language models (VLMs) have demonstrated remarkable capabilities in visual understanding, reasoning, and natural-language interaction, creating new opportunities for intelligent crop health assessment. However, deploying VLMs on resource-constrained...

    arxiv.org/abs/2611.03557 · PDF

  3. 03

    Contrastive Adapter Training and Consensus Knowledge Distillation for Multi-Source-Free Domain Adaptation in Skin Cancer Diagnosis

    Ali Abedi, Q. M. Jonathan Wu, Ning Zhang, Farhad Pourpanah

    cs.CV · cs.AI

    Skin cancer diagnosis, particularly differentiating melanoma from benign nevi, is challenging due to the visual similarity between lesions. Although convolutional neural networks (CNNs) and vision transformers (ViTs) have shown promising performance, their effectiveness often deteriorates on data from heterogeneous clinical sources. Conventional domain adaptation methods address domain shift but require access to source data during...

    arxiv.org/abs/2611.03528 · PDF

  4. 04

    Progressive Multi-Scale Super-Resolution via Cascaded Bicubic Anchors and Inter-Scale Mutual Refinement

    Chun-An Lin, Yu-Chia Chang, Chi-Mao Fan, Yen-Chieh Ouyang, Tsung-Jung Liu

    cs.CV · cs.LG · eess.IV

    Super-resolution networks are trained for one magnification factor, so several output resolutions require several models. We propose PMS-SR, a progressive single-input multiple-output network that produces x2, x4, and x8 results in one forward pass, with a Transformer backbone on the low-resolution grid. In Stage 1, each scale is predicted as a residual over the detached bicubic upsampling of the previous scale's prediction. With Dirac and...

    arxiv.org/abs/2611.03390 · PDF

  5. 05

    Every Pixel Is an Option: A System One Model for Medical Ultrasound Biometry

    Moein Heidari, Junbo Rao, Yudan Chen, Yasamin Medghalchi, River Jiang, Wenjin Chen, David J. Foran, Jasmine Grewal,...

    cs.CV · cs.LG

    **Purpose:** Ultrasound biometry is widely used across various clinical applications, including prenatal and cardiac examinations, to obtain quantitative measurements by placing calipers at anatomical landmarks. However, these measurements remain subject to interoperator variability as they rely largely on manual caliper placement. Conventional methods often use specialized prediction heads for different ultrasound tasks, whereas...

    arxiv.org/abs/2611.03360 · PDF

  6. 06

    Visual-to-Executable Procedural Reconstruction of Buildings

    Zichong Zhu, Zhihao Liu, Andrei Sharf, Zhanglin Cheng

    cs.CV · cs.AI

    Procedural modeling offers compact, editable, and reusable representations for architectural content, but building such models still depends heavily on manually authored grammars. We study image-based procedural building reconstruction from in-the-wild images, with the goal of recovering an executable procedural description that can be instantiated as an editable 3D building asset. Because a single image provides only partial and...

    arxiv.org/abs/2611.03143 · PDF

  7. 07

    Multimodal Prompt Learning with Dual-Granularity Contrastive Alignment for Preoperative Prediction of Lung Adenocarcinoma Invasiveness Using 3D CT

    Qing Huang, Xiaotong Tan, Lintong Yao, Wufeng Xue, Ruobing Huang, Dong Ni, Hao Wu, Tian Xiao, Jun Cheng

    cs.CV · cs.AI

    Accurate preoperative prediction of lung adenocarcinoma invasiveness is important for surgical planning and individualized treatment. However, overlapping CT appearances make it challenging to distinguish invasive adenocarcinoma (IAD) from Pre-IAD lesions. We propose a multimodal prompt-learning framework with dual-granularity image-text alignment for 3D CT-based IAD classification. A 3D ResNet-CBAM encoder extracts global and spatial visual...

    arxiv.org/abs/2611.03109 · PDF

  8. 08

    MIRA: Reinforcing Multimodal Reasoning via Deceptive Contextual Augmentation

    Zhihan Yin, Jianxin Liang, Yifeng Yao, Nonghai Zhang, and Bingyue Peng, Chunguang Qie, Huishuai Zhang, Dongyan Zhao

    cs.CV · cs.AI

    While Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced multimodal reasoning, existing frameworks suffer from a critical "perception-reasoning gap." Due to an over-reliance on seemingly relevant visual tokens, even minor perceptual perturbations can propagate through the reasoning process, leading to compounding hallucinations. To address this issue, we propose MIRA, a training framework that improves robustness...

    arxiv.org/abs/2611.03087 · PDF

  9. 09

    VideoEditor-MoE: Scaling Complex Video Editing with Mixture of Experts

    Xiao Cao, Fuchen Long, Yansong Qu, Wen Xiao, Xin Zhang, Xinlong Sun, Xi Chen, Zhiyong Huang

    cs.CV · cs.AI

    Complex video editing requires understanding complex instructions while jointly fulfilling multiple editing requests. Meeting these demands through dense model scaling substantially increases computational cost. We introduce VideoEditor-MoE, the first open-source mixture-of-experts framework for video editing. Beyond sparse MLP-MoE layers, MoE-Attention expands attention capacity through routed key--value experts while preserving global...

    arxiv.org/abs/2611.03043 · PDF

  10. 10

    Bayesian Sequential Optimal Experimental Design for Single-Pixel Imaging using Reinforcement Learning

    Marcos Antonio Obando, Tianyuan Wang, Tanja Tarvainen, Tristan van Leeuwen, Felix Lucka

    cs.CV · cs.LG

    Adaptive compressed sensing (CS) aims to select the most informative measurements sequentially, which is crucial for many modern imaging systems. This task can be formulated as a Bayesian sequential optimal experimental design (sOED) problem, where each new acquisition is chosen to maximally reduce uncertainty about the unknown image given prior information and subsequent data provided by acquisitions. However, in single-pixel imaging (SPI),...

    arxiv.org/abs/2611.03042 · PDF

  11. 11

    Q-CamTuning: A Multimodal Large Language Model for Fine-Grained Quality Reasoning in Livestreaming Camera Tuning

    Yanchao Bi, Pengfei Chen, Yulong Yan, Qian Zhang, Biao Wang, Leida Li

    cs.CV · cs.AI

    With the popularization of livestreaming applications, automatic camera tuning has become indispensable for ordinary users to enjoy high Quality of Experience (QoE). However, the existing Image Quality Assessment (IQA) methods face two challenges in camera tuning. First, they struggle to identify subtle quality difference between images, which is common in camera tuning. Second, the ability to explain fine-grained differences and to provide...

    arxiv.org/abs/2611.03007 · PDF

  12. 12

    One Image Is Enough: Self-Generated Supervision for Personalizing Human Video Diffusion at Test Time

    Sadman Rakib Pinon, Adamo Orsini, Yanis Falaki, Linlian Jiang, Jacob Kingi, Yang Wang, Xinxin Zuo

    cs.CV · cs.GR · cs.LG

    Pose-driven human video diffusion animates a person from a single reference image and a target pose sequence, yet it struggles to preserve identity, rendering the face and garments unfaithfully as the pose departs from it. Personalization is the standard remedy, but its supervision is missing: one image fixes identity at a single pose, while a multi-pose subject video cannot be assumed in practice. Instead, we synthesize the missing...

    arxiv.org/abs/2611.02964 · PDF

  13. 13

    Balancing Representations by Identifying and Generating Under-represented Data

    Filipe Laitenberger, Hirokatsu Kataoka, Yuki Asano, Cees Snoek, Mohammadreza Salehi

    cs.CV · cs.AI

    Self-supervised learning inherits the coverage of its source data. When an unlabeled corpus is long-tailed, the representation becomes dense around frequent modes and thin where coverage is weak. Objectives for long-tailed SSL reweight the images already in the corpus and add no new ones. We introduce BRIDGE (Balancing Representations by Identifying and Generating Under-represented Data), a label-free feedback loop around the source set. The...

    arxiv.org/abs/2611.02952 · PDF

  14. 14

    RouteREPA: Routed Representation Alignment for Just Image Transformers

    Yi Tan, Beier Zhu, Sirui Chen, Cheng Chen, Xingyu Zhu, Yuan Zhou, Zhenshan Tan, Tianrun Chen, Hanwang Zhang

    cs.CV · cs.LG

    Representation alignment (REPA) is widely used to accelerate the training of latent-space diffusion transformers (DiTs). However, applying it to pixel-space models such as Just Image Transformers (JiT) is challenging. Our analysis reveals a pronounced representation conflict between discriminative alignment and pixel-space generation. Compared with its latent counterpart, JiT learns representations that are substantially less aligned with...

    arxiv.org/abs/2611.02941 · PDF

  15. 15

    Training-Time Domain Transfer for Generator-Free Diagnostics on Novel Modalities in Computational Pathology

    Julia A. Mielcarz, Andrea Camilloni, Nita Mulliqi, Jessica A. Frank, Anders Blilie, Emilius A. M. Janssen, Martin...

    cs.CV · cs.AI

    Novel imaging modalities promise improved diagnostics, but AI development is constrained by scarce training data. Inference-time domain transfer can address this by mapping novel modalities to established ones, enabling reuse of existing diagnostic models. However, this introduces hallucination risks, computational overhead, and regulatory complexity. Inspired by sim-to-real transfer, we propose training-time domain transfer, generating...

    arxiv.org/abs/2611.02931 · PDF

  16. 16

    Unlocking the Potential of Contrastive Regularization for Diffusion Transformer Training

    Yi Tan, Beier Zhu, Sirui Chen, Yunzhe Lin, Yuan Zhou, Cheng Chen, Xingyu Zhu, Tianrun Chen, Yanbin Hao, Hanwang Zhang

    cs.CV · cs.LG

    Representation regularization has emerged as an effective way to improve diffusion transformer training. Yet one of the most canonical regularizers--InfoNCE-style contrastive learning--remains largely underexplored in this setting. We naturally ask a question: can standard contrastive learning serve as an effective regularizer for diffusion transformers? Surprisingly, we find that naive InfoNCE regularization brings only marginal gains. Our...

    arxiv.org/abs/2611.02921 · 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.