cs.CV · 2026-07-01 · No. 40

Computer Vision and Pattern Recognition, 2026-07-01.

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

01 — The papers

24 entries
  1. 01

    FLORA: A deep learning approach to predict forest attributes from heterogeneous LiDAR data

    Emilie Vautier, Clément Mallet, Cédric Vega

    cs.CV · cs.AI

    Forest attributes are essential for national-scale resource monitoring. Airborne LiDAR metrics are among the auxiliary variables most strongly correlated with forest attributes used in National Forest Inventory (NFI) estimates. However, producing wall-to-wall predictions remains challenging when LiDAR data are acquired under heterogeneous conditions. As national LiDAR programs expand across Europe, variability in sensors, flight parameters,...

    arxiv.org/abs/2606.32023 · PDF

  2. 02

    Automated Background Swapping for Robustness against Spurious Backgrounds

    Cesar Roder, Kajetan Schweighofer

    cs.CV · cs.LG

    Classifiers based on Deep Neural Networks exhibit strong performance across domains, yet can fail catastrophically if they rely on spurious correlations, i.e., features that are predictive of the target label in the training data but are not causally linked and thus fail to generalize. For the vision domain, many such spurious correlations manifest themselves within the background of the image, where only the foreground is predictive of the...

    arxiv.org/abs/2606.32018 · PDF

  3. 03

    LUNA: Learning Universal 3D Human Animation Beyond Skinning

    Peng Li, Rawal Khirodkar, Junxuan Li, Yuan Dong, Chen Cao, Yuan Liu, Wenhan Luo, Yike Guo, Shunsuke Saito

    cs.CV · cs.AI

    Creating photorealistic, animatable 3D human avatars from monocular images still largely depends on Linear Blend Skinning (LBS) and parametric body models, which constrain expressivity and often introduce artifacts due to imperfect fitting. We propose LUNA, an LBS-free universal neural animation model that directly maps multiple 2D controls like images, keypoints, sketches, and unseen characters into 3D Gaussian deformations, bypassing...

    arxiv.org/abs/2606.31981 · PDF

  4. 04

    Attend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM Inference

    Zhaoyang Luo, Runmin Dong, Miao Yang, Fan Wei, Yushan Lai, Bin Luo, Haohuan Fu

    cs.CV · cs.AI

    Multimodal large language models (MLLMs) increasingly process long visual-token sequences, increasing the overall inference computation. Existing acceleration methods usually remove visual tokens or skip visual-token updates in entire layers, but these coarse strategies may discard fine-grained evidence or suppress useful operators together with redundant ones. In this paper, we study visual-token computation from an answer-observable...

    arxiv.org/abs/2606.31903 · PDF

  5. 05

    Real-Time Source-Free Object Detection

    Sairam VCR, Varun Gopal, Poornima Jain, Vineeth N Balasubramanian, Muhammad Haris Khan

    cs.CV · cs.AI

    Real-world detectors for autonomous driving, surveillance, and robotics must handle domain-shifts under strict latency and memory constraints, yet existing source-free object detection (SFOD) methods rely on heavyweight architectures that prioritize accuracy alone. We show this trade-off is unnecessary: building on YOLOv10, an NMS-free dual-head detector, we achieve state-of-the-art adaptation accuracy while being faster and more compact. We...

    arxiv.org/abs/2606.31834 · PDF

  6. 06

    Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning

    Junha Jung, Minbyul Jeong, Suhyeon Lim, Sungwook Jung, Jaehoon Yun, Taeyun Roh, Mujeen Sung, Jaewoo Kang

    cs.CV · cs.AI

    Recent multimodal large language models have shown great promise in clinical image reasoning, but existing post-training pipelines remain predominantly outcome-centric, relying on final answer correctness or sequence-level preferences. This suffers from sparse credit assignment, making it difficult to optimize the reasoning process essential for clinical applications. Our analysis reveals that cascading errors from early-stage reasoning...

    arxiv.org/abs/2606.31825 · PDF

  7. 07

    JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering

    Ziyuan Liu, Ruifei Zhu, Ouqiao Ma, Yuantao Gu

    cs.CV · cs.AI

    Remote sensing change detection (CD) traditionally focuses on pixel-level binary segmentation, which identifies where changes occur but neither what nor why. To bridge this semantic gap, we introduce JL1-CC&QA, a multi-task benchmark that extends the JL1-CD dataset with two complementary annotation layers: change captioning (CC) and change question answering (QA). Built upon 5,000 bi-temporal image pairs acquired by the Jilin-1 satellite at...

    arxiv.org/abs/2606.31745 · PDF

  8. 08

    WIDER-FAIR: An Annotated Version of the WIDER-FACE Dataset for Fairness Evaluation

    Maxime Moussi, Benoît Ronval, Siegfried Nijssen, Félicien Schiltz

    cs.CV · cs.LG

    The deployment of face detection models in real-world applications raises important fairness concerns, as these systems may showcase performance disparities across demographic groups. A key obstacle to studying and mitigating such biases is the lack of face detection datasets with sensitive feature annotations. To address this gap, we introduce WIDER-FAIR, a new dataset built on the widely used WIDER-FACE benchmark, manually annotated with...

    arxiv.org/abs/2606.31704 · PDF

  9. 09

    Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models

    Enrico Cassano, Riccardo Renzulli, Rayyan Ahmed, Marco Grangetto, Stephan Alaniz

    cs.CV · cs.AI

    Sparse autoencoders (SAEs) have recently been proposed as interpretable tools for concept-level manipulation, under the assumption that isolated features can serve as controllable intervention points. In this work, we systematically evaluate this assumption in the context of object erasure and steering in diffusion models. We show that while SAEs reliably detect and localize semantic concepts within diffusion model activations, direct...

    arxiv.org/abs/2606.31699 · PDF

  10. 10

    Histogram-constrained Image Generation

    Haoming Liu, Yuanhe Guo, Yijia Cao, Shenji Wan, Hongyi Wen

    cs.CV · cs.AI · cs.LG

    Diffusion models have emerged as a dominant paradigm in generative modeling, enabling high-fidelity sampling from complex data distributions. Despite impressive capabilities, controlling diffusion models to produce outputs aligned with user intent remains an open challenge, especially when balancing global coherence with local precision. Existing control mechanisms vary in the granularity of their conditioning signals. For example, textual...

    arxiv.org/abs/2606.31683 · PDF

  11. 11

    WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models

    Ting-Bing Xu, Jiacheng Sui, Zhe Gao, Kewei Shi, Wenjin Yang, Zhicheng Liu, Zhaoxu Sun, Mingchao Sun, Hongyu Pan, Fan...

    cs.CV · cs.AI

    Despite rapid progress in interactive world models (IWMs), existing benchmarks evaluate action following only at trajectory level and ignore memory and interaction physics. We introduce WorldRoamBench, an open-world benchmark for long-horizon stability across four dimensions, each with tailored innovations: (i) Action: per-frame action metric bypassing cross-model semantic scale disparity and exposing failures hidden by trajectory; (ii)...

    arxiv.org/abs/2606.31672 · PDF

  12. 12

    Sparsity-Inducing Divergence Losses for Biometric Verification

    Dimitrios Koutsianos, Ladislav Mošner, Yannis Panagakis, Themos Stafylakis

    cs.CV · cs.AI

    Performance in face and speaker verification is largely driven by margin-penalty softmax losses such as CosFace and ArcFace. Recently introduced $α$-divergence loss functions offer a compelling alternative, particularly due to their ability to induce sparse solutions (when $α>1$). However, standard geometric margins are designed for the softmax function and do not naturally extend to this generalized probabilistic framework. In this paper we...

    arxiv.org/abs/2606.31664 · PDF

  13. 13

    Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation

    Ali Zia, Muhammad Umer Ramzan, Abdelwahed Khamis, Usman Ali, Abdul Rehman

    cs.CV · cs.AI

    Radar sensors provide reliable perception under adverse weather and lighting conditions, but their sparse, noisy, and weakly semantic measurements make dense semantic segmentation challenging. Most existing radar segmentation methods rely on grid-based encodings and pairwise interactions, which struggle to capture the higher-order relational structure formed by multiple radar returns from the same physical object. We introduce a unified...

    arxiv.org/abs/2606.31609 · PDF

  14. 14

    Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models

    Nikolai Röhrich, Julian Gleißner, Ahmed H. A. Ibrahim, Silvan Mertes, Tobias Huber

    cs.CV · cs.AI · cs.LG

    Semantic segmentation models struggle with data sparsity and rare or visually diverse regions, e.g., dense regions or small objects in aerial or autonomous mobility data. While synthetic augmentation is an appealing solution, directly generating new labeled data risks misalignment of labels and generated pixels. Existing solutions to this problem often rely on external models, or employ coarse heuristics such as indiscriminately augmenting...

    arxiv.org/abs/2606.31603 · PDF

  15. 15

    Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning

    Kaitao Chen, Weiqian Zhao, Jiamin Wu, Qihao Zheng, Shangquan Sun, Chunfeng Song, Xiaosong Wang, Mu Zhou, Mianxin Liu

    cs.CV · cs.AI

    Vision-language models (VLMs) combining reinforcement learning (RL) ignite remarkable progress in multimodal reasoning, yet still struggle with medical images, which typically exhibit extremely sparse visual evidence to inform clinical decision-making. We recognize that pruning visual tokens outside the grounding region greatly enhances medical reasoning. However, a united RL framework for active visual token pruning (VTP) and medical...

    arxiv.org/abs/2606.31599 · PDF

  16. 16

    DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers

    Shun Kenney, Teppei Suzuki

    cs.CV · cs.AI

    The remarkable scalability of Transformers has expanded their application to 3D computer vision, where camera-aware positional encoding is crucial for providing spatial cues in multi-view geometry. Recent advancements have established the practice of using camera parameters -- such as extrinsics or projection matrices -- as relative positional encoding into the query, key, and value vectors of the attention mechanism. However, when scaling up...

    arxiv.org/abs/2606.31585 · PDF

  17. 17

    Localized Conformal Prediction for Image Classification with Vision-Language Models

    Clément Fuchs, Tim Bary, Benoît Macq

    cs.CV · cs.LG

    Conformal predictions have attracted significant attention in the field of uncertainty quantification, mainly because of their strong marginal coverage guarantees. Full conditional guarantee is not an attainable goal, a well known fact in conformal predictions literature. As a result, several approaches have tried to approximate this behavior by adapting the conformal sets of test-time samples according to their similarity to calibration...

    arxiv.org/abs/2606.31577 · PDF

  18. 18

    Temperature Field Reconstruction of Tungsten Monoblock Divertor on EAST using Physics-aware Neural Operator Transformer

    Zikang Yan, Xiao Wang, Qingquan Yang, Zhendong Yang, Gaoting Chen, Zehua Chen, Bo Jiang, Jin Tang, Guosheng Xu

    cs.CV · cs.AI · cs.LG

    Accurate modeling of the divertor temperature field is essential for preventing material melting and damage and for extending the service life of fusion devices. However, conventional numerical methods, such as the Finite Element Method (FEM), are computationally expensive and therefore unsuitable for real-time applications. Therefore, a fast and generalizable method is required for real-time reconstruction of the divertor temperature field...

    arxiv.org/abs/2606.31574 · PDF

  19. 19

    Mitigating Positional Leakage in 3D Masked Autoencoders for Robust Representation Learning

    Xu Yan, Huiqun Wang, Chen Wang, Lei Ren, Di Huang

    cs.CV · cs.AI

    Masked autoencoding has emerged as a prominent paradigm for self-supervised learning on 3D point clouds, achieving competitive performance across downstream tasks. Unlike its 2D counterpart, 3D masked autoencoding directly reconstructs spatial coordinates, making it inherently susceptible to positional leakage. In this work, we identify that the decoder in existing 3D MAE frameworks tends to over-rely on positional information, which weakens...

    arxiv.org/abs/2606.31570 · PDF

  20. 20

    Temporal Preservation over Processing: Diagnosing and Designing Spatiotemporal Single-Stage Video Detectors

    Karam Tomotaki-Dawoud, Anna Hilsmann, Peter Eisert, Sebastian Bosse

    cs.CV · cs.AI

    Single-stage video object detectors are increasingly deployed in time-critical applications, yet it remains unclear whether these models genuinely reason over temporal context or merely exploit a single informative frame-a gap hidden by standard metrics, which reward correct predictions regardless of how they are reached. We address this from two complementary directions: first, we propose TemporalLens, a model-agnostic diagnostic framework...

    arxiv.org/abs/2606.31421 · PDF

  21. 21

    Visual Semantic Entropy: Do Vision Language Models Recognize Visual Ambiguity?

    Ta Duc Huy, Trang Nguyen, Townim Chowdhury, Ankit Yadav, Minh-Son To, Zhibin Liao, Johan W. Verjans, Vu Minh Hieu Phan

    cs.CV · cs.AI · cs.CL

    Vision-language models can produce confident answers on visually ambiguous inputs, resulting in biased predictions. Common entropy-based methods, such as Semantic Entropy (SE), rely on output diversity. Yet our analysis shows that overconfident visual embeddings suppress output diversity under stochastic decoding, causing SE to underestimate uncertainty in such cases. Recent methods instead probe output diversity through input perturbations,...

    arxiv.org/abs/2606.31407 · PDF

  22. 22

    CLIMB: Centroid-Based Hierarchical Memory for Online Continual Self-Supervised Learning

    Julien Lefebvre, Stefan Duffner, Mathieu Lefort

    cs.CV · cs.AI

    Online Continual Self-Supervised Learning (OCSSL) aims to learn representations from a continuous stream of unlabeled data, without knowledge of task boundaries and under memory constraints. Existing methods rely either on replay buffers that exploit latent space structure, or on regularization alone. We present CLIMB (Continual Learning with Intelligent Memory Bank), which combines both simultaneously. Our method introduces a hierarchical...

    arxiv.org/abs/2606.31275 · PDF

  23. 23

    Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents

    Xueqiao Sun, Xiaohan Wang, Ludwig Schmidt, Serena Yeung-Levy, Yuhui Zhang

    cs.CV · cs.AI · cs.CL · cs.CY · cs.LG

    Computer-use agents, which leverage multimodal large language models (MLLMs) to operate computers and complete tasks, have attracted significant attention for their utility and versatility. A major challenge in developing these agents is collecting large-scale, high-quality trajectories. The standard approach generates synthetic data through a self-improving loop: an agent is placed in a verifiable environment and iteratively fine-tuned on...

    arxiv.org/abs/2606.31270 · PDF

  24. 24

    Distilling Temporal Coherence into 2D Networks for Transrectal Ultrasound Prostate Video Segmentation

    Dong Yeong Kim, JunGyu Lee, Jaewon Choi, June Young Seo, Myeongseop Kim, Jinwook Choi, Taek Min Kim, Young-Gon Kim

    cs.CV · cs.AI

    Real-time video segmentation of the prostate in Transrectal Ultrasound (TRUS) is essential for image-guided interventions. While conventional 2D methods suffer from inter-frame inconsistencies by disregarding temporal context, 3D architectures incur prohibitive latency. To resolve this dilemma, we present a Temporally Consistent Learning Framework that distills temporal coherence into a 2D network during training, preserving single-frame...

    arxiv.org/abs/2606.31198 · 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.