SkipSR：通过令牌跳过实现更快的超分辨率
SkipSR: Faster Super Resolution with Token Skipping
AI总结：
SkipSR通过从低分辨率输入识别低细节区域并跳过其计算，仅对需要细化的区域进行超分辨率处理，在保持感知质量的同时，将720p视频的端到端延迟降低高达60%。
摘要：
基于扩散的超分辨率（SR）是视频生成和视频修复中的关键组成部分，但速度慢且成本高，限制了向更高分辨率和更长视频的可扩展性。我们的关键见解是，视频中的许多区域本质上细节较少，从细化中获益甚微，然而当前方法对所有像素进行统一处理。为了利用这一点，我们提出了SkipSR，一个简单的框架，通过直接从低分辨率输入中识别低细节区域，然后完全跳过这些区域的计算，仅对需要细化的区域进行超分辨率处理，从而加速视频SR。这种简单而有效的策略在标准扩散SR模型和单步扩散SR模型中均能保持感知质量，同时显著减少计算量。在标准SR基准测试中，我们的方法在720p视频上实现了比先前模型高达60%的端到端延迟降低，且质量无明显损失。视频演示可在https://rccchoudhury.github.io/skipsr/ 获取。
英文摘要：
Diffusion-based super-resolution (SR) is a key component in video generation and video restoration, but is slow and expensive, limiting scalability to higher resolutions and longer videos. Our key insight is that many regions in video are inherently low-detail and gain little from refinement, yet current methods process all pixels uniformly. To take advantage of this, we propose SkipSR, a simple framework for accelerating video SR by identifying low-detail regions directly from low-resolution input, then skipping computation on them entirely, only super-resolving the areas that require refinement. This simple yet effective strategy preserves perceptual quality in both standard and one-step diffusion SR models while significantly reducing computation. In standard SR benchmarks, our method achieves up to 60% faster end-to-end latency than prior models on 720p videos with no perceptible loss in quality. Video demos are available at https://rccchoudhury.github.io/skipsr/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
