SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration

Jianyi Wang; Zhijie Lin; Meng Wei; Yang Zhao; Ceyuan Yang; Chen Change Loy; Lu Jiang

doi:10.1109/cvpr52734.2025.00207

CVPR2025顶会

SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration

Jianyi Wang, Zhijie Lin, Meng Wei, Yang Zhao, Ceyuan Yang, Chen Change Loy, Lu Jiang

arXiv DOI 出版方

2025年份

15顶会引用

摘要

Figure 1. Speed and performance comparisons. SeedVR demonstrates impressive restoration capabilities, offering fine details and enhanced visual realism. Despite its 2.48B parameters, SeedVR is over 2× faster than existing diffusion-based video restoration approaches [20, 64, 82]. With delicate designs, SeedVR is as efficient as the Stable Diffusion Upscaler [2], even with five times the parameter count.