FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhuang, Junhao, Guo, Shi, Cai, Xin, Li, Xiaohui, Liu, Yihao, Yuan, Chun, Xue, Tianfan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912647068254208
author Zhuang, Junhao
Guo, Shi
Cai, Xin
Li, Xiaohui
Liu, Yihao
Yuan, Chun
Xue, Tianfan
author_facet Zhuang, Junhao
Guo, Shi
Cai, Xin
Li, Xiaohui
Liu, Yihao
Yuan, Chun
Xue, Tianfan
contents Diffusion models have recently advanced video restoration, but applying them to real-world video super-resolution (VSR) remains challenging due to high latency, prohibitive computation, and poor generalization to ultra-high resolutions. Our goal in this work is to make diffusion-based VSR practical by achieving efficiency, scalability, and real-time performance. To this end, we propose FlashVSR, the first diffusion-based one-step streaming framework towards real-time VSR. FlashVSR runs at approximately 17 FPS for 768x1408 videos on a single A100 GPU by combining three complementary innovations: (i) a train-friendly three-stage distillation pipeline that enables streaming super-resolution, (ii) locality-constrained sparse attention that cuts redundant computation while bridging the train-test resolution gap, and (iii) a tiny conditional decoder that accelerates reconstruction without sacrificing quality. To support large-scale training, we also construct VSR-120K, a new dataset with 120k videos and 180k images. Extensive experiments show that FlashVSR scales reliably to ultra-high resolutions and achieves state-of-the-art performance with up to 12x speedup over prior one-step diffusion VSR models. We will release the code, pretrained models, and dataset to foster future research in efficient diffusion-based VSR.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12747
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
Zhuang, Junhao
Guo, Shi
Cai, Xin
Li, Xiaohui
Liu, Yihao
Yuan, Chun
Xue, Tianfan
Computer Vision and Pattern Recognition
Diffusion models have recently advanced video restoration, but applying them to real-world video super-resolution (VSR) remains challenging due to high latency, prohibitive computation, and poor generalization to ultra-high resolutions. Our goal in this work is to make diffusion-based VSR practical by achieving efficiency, scalability, and real-time performance. To this end, we propose FlashVSR, the first diffusion-based one-step streaming framework towards real-time VSR. FlashVSR runs at approximately 17 FPS for 768x1408 videos on a single A100 GPU by combining three complementary innovations: (i) a train-friendly three-stage distillation pipeline that enables streaming super-resolution, (ii) locality-constrained sparse attention that cuts redundant computation while bridging the train-test resolution gap, and (iii) a tiny conditional decoder that accelerates reconstruction without sacrificing quality. To support large-scale training, we also construct VSR-120K, a new dataset with 120k videos and 180k images. Extensive experiments show that FlashVSR scales reliably to ultra-high resolutions and achieves state-of-the-art performance with up to 12x speedup over prior one-step diffusion VSR models. We will release the code, pretrained models, and dataset to foster future research in efficient diffusion-based VSR.
title FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.12747