International Journal of Computer Vision最新文献_第2页

HR-INR: Continuous Space-Time Video Super-Resolution via Event Camera HR-INR：基于事件相机的连续时空视频超分辨率

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-07 DOI: 10.1007/s11263-026-03034-4

Yunfan Lu, Yusheng Wang, Zipeng Wang, Pengteng Li, Bin Yang, Hui Xiong

{"title":"HR-INR: Continuous Space-Time Video Super-Resolution via Event Camera","authors":"Yunfan Lu, Yusheng Wang, Zipeng Wang, Pengteng Li, Bin Yang, Hui Xiong","doi":"10.1007/s11263-026-03034-4","DOIUrl":"https://doi.org/10.1007/s11263-026-03034-4","url":null,"abstract":"Continuous space-time video super-resolution (C-STVSR) aims to simultaneously enhance video resolution and frame rate at an arbitrary scale. Recently, implicit neural representation (INR) has been applied to video restoration, representing videos as implicit fields that can be decoded at an arbitrary scale. However, existing INR-based C-STVSR methods typically rely on only two frames as input, leading to insufficient inter-frame motion information. Consequently, they struggle to capture fast, complex motion and long-term dependencies (spanning more than three frames), hindering their performance in dynamic scenes. In this paper, we propose a novel C-STVSR framework, named HR-INR, which captures both h olistic dependencies and r egional motions based on INR. It is assisted by an event camera – a novel sensor renowned for its high temporal resolution and low latency. To fully utilize the rich temporal information from events, we design a feature extraction consisting of (1) a regional event feature extractor – taking events as inputs via the proposed event temporal pyramid representation to capture the regional nonlinear motion and (2) a holistic event-frame feature extractor for long-term dependence and continuity motion. We then propose a novel INR-based decoder with spatiotemporal embeddings to capture long-term dependencies with a larger temporal perception field. We validate the effectiveness and generalization of our method on four datasets (both simulated and real data), showing the superiority of our method. The project page is available at https://github.com/yunfanLu/HR-INR .","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"3 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149130296","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

Controllable Human-Object Interaction Synthesis via Progressive and Invertible Condition Injection 基于渐进可逆条件注入的可控人-物交互综合

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03052-2

Xiaotong Lin,Tianming Liang,Heng Li,Jiangxin Sun,Jianguo Zhang,Jian-Fang Hu

引用次数: 0

Fix Your Downsampling ASAP! Aliasing and Sinc Artifact Free Pooling in the Fourier Domain 尽快修复你的降级采样！傅立叶域中的混叠和无伪影池

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03005-9

Julia Grabinski,Steffen Jung,Janis Keuper,Margret Keuper

{"title":"Fix Your Downsampling ASAP! Aliasing and Sinc Artifact Free Pooling in the Fourier Domain","authors":"Julia Grabinski,Steffen Jung,Janis Keuper,Margret Keuper","doi":"10.1007/s11263-026-03005-9","DOIUrl":"https://doi.org/10.1007/s11263-026-03005-9","url":null,"abstract":"Abstract Convolutional Neural Networks (CNNs) are successful in various computer vision tasks. From an image and signal processing point of view, this success is counter-intuitive, as the inherent spatial pyramid design of most CNNs is apparently violating basic signal processing laws, i.e. the Sampling Theorem in their downsampling operations. This issue has been broadly neglected until recent work in the context of adversarial attacks and distribution shifts showed that there is a strong correlation between the vulnerability of CNNs and aliasing artifacts induced by bandlimit-violating downsampling. As a remedy, we propose an alias-free downsampling operation in the frequency domain, denoted Frequency Low Cut Pooling (FLC Pooling) which we further extend to Aliasing and Sinc Artifact-free Pooling (ASAP) . ASAP is alias-free and removes further artifacts from sinc-interpolation. Our experimental evaluation on ImageNet-1k, ImageNet-C and CIFAR datasets on various CNN architectures demonstrates that networks using FLC Pooling and ASAP as downsampling methods learn more stable features as measured by their robustness against common corruptions and adversarial attacks, while maintaining a clean accuracy similar to the respective baseline models.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"148 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149090950","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

AdaEA++: Enhanced Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferability ada++：增强自适应模型集成对抗攻击，提高对抗可转移性

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03054-0

Bin Chen,Jia-Li Yin,Bo-Hao Chen,Ximeng Liu,Yuanlong Yu

引用次数: 0

SEE: See Everything Every Time - Adaptive Brightness Adjustment for Broad Light Range Images via Events 参见：每次看到的一切-自适应亮度调整通过事件的广光范围图像

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03033-5

Yunfan Lu,Xiaogang Xu,Hao Lu,Yanlin Qian,Pengteng Li,Huizai Yao,Bin Yang,Junyi Li,Qianyi Cai,Weiyu Guo,Hui Xiong

{"title":"SEE: See Everything Every Time - Adaptive Brightness Adjustment for Broad Light Range Images via Events","authors":"Yunfan Lu,Xiaogang Xu,Hao Lu,Yanlin Qian,Pengteng Li,Huizai Yao,Bin Yang,Junyi Li,Qianyi Cai,Weiyu Guo,Hui Xiong","doi":"10.1007/s11263-026-03033-5","DOIUrl":"https://doi.org/10.1007/s11263-026-03033-5","url":null,"abstract":"Abstract Event cameras, with a high dynamic range exceeding 120 dB , significantly outperform traditional embedded cameras, robustly recording detailed changing information under various lighting conditions, including both low- and high-light situations. However, recent research on utilizing event data has primarily focused on low-light image enhancement, neglecting image enhancement and brightness adjustment across a broader range of lighting conditions, such as normal or high illumination. Based on this, we propose a novel research question: how to employ events to enhance and adaptively adjust the brightness of images captured under broad lighting conditions? To investigate this question, we first collected a new dataset, SEE-600K, consisting of 610,126 images and corresponding events across 202 scenarios, each featuring an average of four lighting conditions with over a 1000-fold variation in illumination. Subsequently, we propose a framework that effectively utilizes events to smoothly adjust image brightness through the indication of custom brightness via user-introduced prompts. Our framework captures color through sensor patterns, uses cross-attention to model events as a brightness dictionary, and adjusts the image’s dynamic range to form a broad light-range representation (BLR), which is then decoded at the pixel level based on the user-introduced brightness prompt. Experimental results demonstrate that our method not only performs well on the low-light enhancement dataset but also shows robust performance on broader light-range image enhancement using the SEE-600K dataset. Additionally, our approach enables pixel-level brightness adjustment, providing flexibility for post-processing and inspiring more imaging applications. The dataset and source code are publicly available at: https://github.com/yunfanLu/SEE.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"14 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149090949","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

Semantic Privacy Protection with Utility Preservation for 3D Point Clouds 三维点云的语义隐私保护与效用保存

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03021-9

Jinchang Zhang,Jiakai Lin,David Crandall,Guoyu Lu

{"title":"Semantic Privacy Protection with Utility Preservation for 3D Point Clouds","authors":"Jinchang Zhang,Jiakai Lin,David Crandall,Guoyu Lu","doi":"10.1007/s11263-026-03021-9","DOIUrl":"https://doi.org/10.1007/s11263-026-03021-9","url":null,"abstract":"Abstract Point cloud data face serious semantic privacy risks during acquisition, transmission, and cross-institutional sharing. Existing methods mostly rely on geometric perturbation or destructive encryption, which can reduce the recognizability of the original class but often impair downstream usability. This paper proposes a class-transfer-based semantic encryption framework for point clouds, aiming to conceal original class information while preserving task utility and supporting authorized recovery. Specifically, we construct a unified latent space with a shared-backbone Normalizing Flow, and combine LoRA and FiLM to achieve parameter-efficient class-conditional adaptation. We further introduce diffusion-guided flow alignment to regularize the latent distribution, construct an energy-based category transition graph, and obtain an optimal class-transfer table through global matching. Then, a latent-space Neural ODE continuously evolves source-class latents into target-class latents, which are decoded into target-class point clouds through the inverse flow. We adopt attacker-oriented metrics, including New-Class Recognition Rate (NCRR), Original-Class Leakage Rate (OCLR), and Original Label Recovery Rate (OLRR), to evaluate privacy and utility. Experiments on classification and segmentation benchmarks show that the proposed method achieves controllable semantic transformation, effectively reduces original-class semantic leakage, preserves downstream learnability in the protected domain, and supports reliable authorized reconstruction.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"26 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149209016","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

RS-vHeat+: An Efficient Remote Sensing Foundation Model Guided by Multi-Modal Fine-Grained Visual Semantics via Heat Conduction RS-vHeat+：基于热传导的多模态细粒度视觉语义的高效遥感基础模型

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03070-0

Huiyang Hu,Peijin Wang,Hanbo Bi,Yingchao Feng,Wenhui Diao,Ziqi Zhang,Kun Fu,Xian Sun

引用次数: 0

Blurring Modal Boundaries: A Unified Survey from Single- to Multi-modal Person Re-ldentification 模糊模态边界：从单一到多模态人再识别的统一调查

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03069-7

Xiao Wang,Bing Wang,Bin Yang,Cuiqun Chen,Xin Xu,Mang Ye

引用次数: 0

CLIDD: Cross-Layer Independent Deformable Description for Efficient and Discriminative Local Feature Representation CLIDD：高效判别局部特征表示的跨层独立可变形描述

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-10-01 DOI: 10.1007/s11263-026-03063-z

Haodi Yao, Fenghua He, Ning Hao, Yao Su

引用次数: 0

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