DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Models

Yeh, Chang-Han, Chin-Yang Lin, Zhixiang Wang, Chi-Wei Hsiao, Ting-Hsuan Chen, Yu-Lun Liu

DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Models: 24 upvotes on Hugging Face Daily Papers, #8 of 27 papers on 2024-07-02. Day-by-day upvote history.

This paper introduces a method for zero-shot video restoration using pre-trained image restoration diffusion models. Traditional video restoration methods often need retraining for different settings and struggle with limited generalization across various degradation types and datasets. Our approach uses a hierarchical token merging strategy for keyframes and local frames, combined with a hybrid correspondence mechanism that blends optical flow and feature-based nearest neighbor matching (latent merging). We show that our method not only achieves top performance in zero-shot video restoration but also significantly surpasses trained models in generalization across diverse datasets and extreme degradations (8times super-resolution and high-standard deviation video denoising). We present evidence through quantitative metrics and visual comparisons on various challenging datasets. Additionally, our technique works with any 2D restoration diffusion model, offering a versatile and powerful tool for video enhancement tasks without extensive retraining. This research leads to more efficient and widely applicable video restoration technologies, supporting advancements in fields that require high-quality video output. See our project page for video results at https://jimmycv07.github.io/DiffIR2VR_web/.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.