arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision

2026-08-14 至 2026-08-14 共收录 3
2605.27616 2026-08-14 cs.CV cs.AI

Not All NVFP4 QAT Recipes Are Equal: How Architecture and Scale Shape Model Quality for Anomaly Segmentation

并非所有 NVFP4 QAT 配方都相同:架构和规模如何影响异常分割的模型质量

Zijian Du, Oleg Rybakov

机构 * NVIDIA

AI总结 本研究通过统一协议评估多种架构、规模和 FP4 量化感知训练 (QAT) 配方在脑肿瘤异常分割任务中的交互作用,发现架构选择对量化鲁棒性影响最大,注意力机制架构对配方选择具有显著韧性,而 CNN 在大规模下受梯度量化配方影响性能下降。

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2026, pp. 7713-7721

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.07694 2026-08-14 cs.CV cs.AI

Compressed-Domain-Aware Online Video Super-Resolution

压缩域感知的在线视频超分辨率

Yuhang Wang, Hai Li, Shujuan Hou, Zhetao Dong, Xiaoyao Yang

机构 * School of Information and Electronics, Beijing Institute of Technology, Beijing, China(信息与电子学院,北京理工大学,北京,中国) Terahertz Science and Application Center, Beijing Institute of Technology, Zhuhai, Guangdong, China(太赫兹科学与应用中心,北京理工大学,珠海,广东,中国)

AI总结 本文提出CDA-VSR方法,通过利用压缩域信息提升在线视频超分辨率的效率和质量,实现比现有方法更高的PSNR和更快的推理速度。

Comments Accepted to CVPR 2026

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026, pp. 33621-33631

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.17492 2026-08-14 cs.CV 版本更新

EvDiff: Event-Based Video Reconstruction using One-Step Diffusion Models

EvDiff:高质视频与事件相机

Weilun Li, Lei Sun, Ruixi Gao, Qi Jiang, Yuqin Ma, Kaiwei Wang, Ming-Hsuan Yang, Luc Van Gool, Danda Pani Paudel

机构 * Zhejiang University(浙江大学) INSAIT UC Merced(加州大学默塞德分校) Google DeepMind(谷歌DeepMind)

AI总结 EvDiff通过基于事件的扩散模型和替代训练框架,从单色事件流生成高质量彩色视频,提升视频生成的保真度和现实感。

Comments Replacement note: This manuscript has been transferred from the CVPR format to the ECCV 2026 format, with the corresponding title and template updated accordingly. The technical content remains largely unchanged from the previous version. (Current version: 21 pages, 6 figures, and 3 tables.) Accepted by ECCV 2026

详情

展开后加载摘要…

URL PDF HTML 收藏