AI RESEARCH
Rethinking Diffusion Model-Based Video Super-Resolution: Leveraging Dense Guidance from Aligned Features
arXiv CS.CV
•
ArXi:2511.16928v2 Announce Type: replace Diffusion model (DM) based Video Super-Resolution (VSR) approaches achieve impressive perceptual quality. However, they suffer from error accumulation, spatial artifacts, and a trade-off between perceptual quality and fidelity, primarily caused by inaccurate alignment and insufficient compensation between video frames.