Research map / Video / Video generation
Harnessing Image Diffusion Prior for Photo-Realistic Video Restoration
Fanghua Yu, Hongyu An, Jinfan Hu, Xinqi Lin, Zhiyuan You, Jian Wang, Hongyang Li, Chao Dong, Jinjin Gu
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Adapts a pretrained image diffusion model's generative prior to video restoration to achieve photo-realistic results with temporal consistency.
Problem
Transferring powerful image diffusion priors to video restoration is hard because stochastic detail synthesis causes temporal inconsistency; existing video restoration methods keep coherence but lose visual fidelity.
Approach
Harnesses a pretrained image diffusion prior for video restoration with a generative video framework that aims to close the gap between image-level quality and video-level stability. Details beyond the abstract are not stated.
Closest papers by meaning
- One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution (NeurIPS 2025 · similarity 0.91)
- Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution (CVPR 2024 · similarity 0.88)
- Spectral Progressive Diffusion for Efficient Image and Video Generation (NeurIPS 2026 · similarity 0.88)
- How I Warped Your Noise: a Temporally-Correlated Noise Prior for Diffusion Models (ICLR 2024 · similarity 0.88)
- VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models (AAAI 2025 · similarity 0.87)
- Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
