首个实现实时扩散视频超分的框架，兼顾速度与画质。
FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
- 三阶段蒸馏+稀疏注意力+微型解码器，提升效率与可扩展性。
- 768x1408视频下达17帧/秒，比前代快12倍。
- 适合追求实时视频增强的研究者与工业应用开发者。
扩散模型虽推动了视频修复发展，但其在真实场景视频超分辨率（VSR）中的应用仍受限于高延迟、高算力及对超高分辨率泛化能力差。本文提出FlashVSR，首个面向实时流式视频超分的扩散模型框架。通过三项创新：(i) 可训练的三阶段蒸馏流水线，支持流式超分；(ii) 局部约束稀疏注意力，减少冗余计算并弥合训练-测试分辨率差距；(iii) 极小条件解码器，加速重建且不损失质量。为支持大规模训练，构建新数据集VSR-120K，包含12万段视频与18万张图像。实验表明，FlashVSR可稳定拓展至超高分辨率，在单张A100 GPU上实现约17 FPS（768x1408视频），较先前一步式扩散模型提速最高达12倍，性能达到当前最优。代码、预训练模型及数据集将开源，以推动高效扩散视频超分研究。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。