Fastvr restores hd video quality quickly using efficient diffusion models
FastVR: Efficient Streaming Video Restoration with One-Step Diffusion
Computer Vision and Pattern Recognition
Summary
High-quality video restoration often takes a lot of computing power, making it hard to use in real-time settings. The authors created FastVR, a system that speeds up this process by simplifying parts of the video enhancement method and smartly focusing on chunks of video frames. This makes it possible to restore full HD videos smoothly and quickly while keeping details and continuity between frames. FastVR was tested on different video types and works better and faster than similar methods.
What this means in practice
- •For video streaming service teams: Enhance live or on-demand 1080p video streams with fast, high-quality restoration that runs on a single GPU in real time.$Commercial implications: Enables video platforms to offer better visual quality efficiently, improving user experience with affordable hardware.
- •For video editing software developers: Integrate fast, one-step diffusion-based restoration into editing tools to improve damaged or low-quality footage without heavy processing delays.
Authors
Xiaoxu Chen, Qin Yang, Haoran Bai, Sibin Deng, Ying Chen
Abstract
Diffusion-based video restoration recovers realistic details, but its practical deployment is limited by two efficiency bottlenecks: costly VAE encoding and decoding, and the quadratic cost of full self-attention in diffusion transformers (DiTs). This paper presents FastVR, a streaming video restoration framework built on a one-step diffusion model, which delivers strong restoration quality and temporal consistency while processing 1080p video at 11 FPS on a single H20 GPU. To improve inference efficiency, FastVR combines a lightweight VAE with chunk-wise causal attention, which substantially reduces the computational cost. During training, it further adopts velocity consistency regularization and continuous trajectory learning, which improve restoration quality. Extensive experiments show that FastVR is more efficient than the evaluated diffusion baselines while achieving state-of-the-art performance on synthetic and real-world benchmarks. We hope that this work supports further progress in the community.