International Journal of Computer Vision最新文献_第3页

DLCL: Deep Learning-Enabled Cooperative Localization for UAV-UGV Team with Adaptive Perception Recovery 基于深度学习的无人机- ugv团队自适应感知恢复协同定位

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03028-2

Veera Venkata Ram Murali Krishna Ra Muvva,Yogesh Chawla,Kunjan Theodore Joseph,Ankita Kalra,Marilyn Wolf,Santosh Pitla

引用次数: 0

DreamMix: Decoupling Object Attributes for Enhanced Editability in Customized Image Inpainting 解耦对象属性，增强自定义图像绘制的可编辑性

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03066-w

Yicheng Yang,Pengxiang Li,Lu Zhang,Liqian Ma,Ping Hu,Siyu Du,Yunzhi Zhuge,Xu Jia,Huchuan Lu

引用次数: 0

Progressive Focused Transformer for Image Restoration 渐进聚焦变压器图像恢复

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03053-1

Wei Long,Jinhua Zhang,Xingyu Zhou,Leheng Zhang,Shuhang Gu

引用次数: 0

Socialality Anchors: Towards Group-Bounded Trajectory Prediction 社会性锚：迈向群体边界轨迹预测

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03076-8

Ziqian Zou,Conghao Wong,Qinmu Peng,Xinge You

引用次数: 0

MC-PanDA++: Simpler, Stronger, and More Robust Domain-Adaptive Panoptic Segmentation MC-PanDA++：更简单，更强大，更稳健的区域自适应全景分割

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03046-0

Ivan Martinović, Josip Šarić, Yuki M. Asano, Siniša Šegvić

引用次数: 0

Boundary-Aware Model with Deformable Feature Warping for Sparse-View Reconstruction 具有可变形特征变形的稀疏视图重构边界感知模型

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03060-2

Liying Yang, Yongqiang Zhang, Chen Liu, Lincheng Li, Xin Yu, Yanyan Liang

引用次数: 0

RDD: Improving Structure from Motion with a Robust Feature Detector and Descriptor RDD：用鲁棒特征检测器和描述子改进运动结构

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03061-1

Gonglin Chen,Tianwen Fu,Haiwei Chen,Wenbin Teng,Hanyuan Xiao,Yajie Zhao

{"title":"RDD: Improving Structure from Motion with a Robust Feature Detector and Descriptor","authors":"Gonglin Chen,Tianwen Fu,Haiwei Chen,Wenbin Teng,Hanyuan Xiao,Yajie Zhao","doi":"10.1007/s11263-026-03061-1","DOIUrl":"https://doi.org/10.1007/s11263-026-03061-1","url":null,"abstract":"Abstract Robust feature detection and description are core components of 3D vision pipelines, yet they remain challenging under large viewpoint, scale, and appearance changes. Recent methods have improved local feature learning, but many still rely on convolutional operators whose local receptive fields limit their ability to capture long-range geometric cues. We present Robust Deformable Detector (RDD), a robust keypoint detector and descriptor that uses deformable transformers to capture global context and geometric invariance. Deformable attention allows the descriptor branch to focus on a sparse set of informative locations, reducing the effective search space while preserving the ability to model long-range relationships. We also collect an Air-to-Ground dataset for training and evaluation, complementing the standard MegaDepth dataset. RDD outperforms state-of-the-art keypoint detection and description methods in sparse matching and also supports semi-dense matching. To support comprehensive evaluation, we introduce two challenging benchmarks: MegaDepth-View, which emphasizes large viewpoint and scale variations, and Air-to-Ground, which targets cross-altitude matching for 3D reconstruction. Project page: https://xtcpete.github.io/rdd/ .","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"12 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149090948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DOME: A Decoupled Offline-Online Memory Externalization Framework for Interpretable Domain-Generalized Face Anti-spoofing 一个解耦的离线-在线内存外化框架，用于可解释域广义人脸反欺骗

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03010-y

Yanting Wu,Ajian Liu,Siyu Xia,Yunlong Wang,Xinyang Song,Jie Gui,Zhenan Sun,Qi Li

引用次数: 0

SLCA++: Unleash the Power of Sequential Fine-Tuning for Continual Learning with Pre-training slca++：释放连续微调的力量，通过预训练进行持续学习

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03041-5

Gengwei Zhang,Liyuan Wang,Guoliang Kang,Ling Chen,Yunchao Wei

引用次数: 0

EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning 基于原型重新平衡的冷启动无范例增量学习弹性特征整合

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-09-28 DOI: 10.1007/s11263-026-03018-4

Simone Magistri, Tomaso Trinci, Albin Soutif-Cormerais, Joost van de Weijer, Andrew D. Bagdanov

{"title":"EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning","authors":"Simone Magistri, Tomaso Trinci, Albin Soutif-Cormerais, Joost van de Weijer, Andrew D. Bagdanov","doi":"10.1007/s11263-026-03018-4","DOIUrl":"https://doi.org/10.1007/s11263-026-03018-4","url":null,"abstract":"Exemplar-free Class Incremental Learning (EFCIL) aims to learn from a sequence of tasks without having access to previous task data. In this paper, we consider the challenging Cold Start scenario in which insufficient data is available in the first task to learn a high-quality backbone. This is especially challenging for EFCIL since it requires high plasticity, resulting in feature drift which is difficult to compensate for in the exemplar-free setting. To address this problem, we propose an effective approach to consolidate feature representations by regularizing drift in directions highly relevant to previous tasks while employing prototypes to reduce task-recency bias. Our approach, which we call Elastic Feature Consolidation++ (EFC++), exploits a tractable second-order approximation of feature drift based on a proposed Empirical Feature Matrix (EFM). The EFM induces a pseudo-metric in feature space which we use to regularize feature drift in important directions and to update Gaussian prototypes. In addition, we introduce a post-training prototype re-balancing phase that updates classifiers to compensate for feature drift. This strategy allows to improve over our previous EFC method by mitigating the misalignment between stored prototypes and the evolving feature space. Extensive experimental results on Tiny-ImageNet, ImageNet-Subset, ImageNet-1K, and DomainNet show that EFC++ achieves a strong stability–plasticity trade-off in Cold Start and outperforms recent exemplar-free baselines. Code is available at https://github.com/simomagi/elastic_feature_consolidation .","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"63 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149067365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0