Stream-DiffVSR: 通过自回归扩散实现低延迟可流式传输视频超分辨率
Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion
AI总结：
Stream-DiffVSR提出一种因果条件扩散框架，通过四步蒸馏去噪器、自回归时间引导模块和轻量时间感知解码器，实现高效在线视频超分辨率，显著降低延迟并提升质量。
摘要：
基于扩散的视频超分辨率（VSR）方法在感知质量上表现优异，但因依赖未来帧和昂贵的多步去噪而难以满足低延迟场景需求。我们提出了Stream-DiffVSR，一种因果条件扩散框架，严格基于过去帧进行高效在线VSR。Stream-DiffVSR集成了四步蒸馏去噪器以实现快速推理，自回归时间引导（ARTG）模块在潜在空间去噪过程中注入运动对齐线索，以及轻量时间感知解码器，其中包含时间处理器模块（TPM）以增强细节和时间一致性。与分块流式推理不同，我们的严格帧到帧因果设计避免了序列级等待，显著降低了时间到第一帧和端到端延迟。Stream-DiffVSR在RTX 4090上处理720p帧耗时0.328秒，并一致优于先前的扩散基基线。与在线最先进的TMP相比，它在感知质量（LPIPS +0.095）方面有所提升，同时将延迟降低超过130倍。此外，Stream-DiffVSR大幅降低了扩散基VSR的时间到第一帧，将初始延迟从超过4600秒减少到0.328秒，使基于扩散的VSR在低延迟在线和流式部署中变得更具实用性。项目页面：https://jamichss.github.io/stream-diffvsr-project-page/
英文摘要：
Diffusion-based video super-resolution (VSR) methods deliver strong perceptual quality but are often unsuitable for latency-sensitive scenarios due to reliance on future frames and expensive multi-step denoising. We propose Stream-DiffVSR, a causally conditioned diffusion framework for efficient online VSR. Operating strictly on past frames, Stream-DiffVSR integrates a four-step distilled denoiser for fast inference, an Auto-regressive Temporal Guidance (ARTG) module that injects motion-aligned cues during latent denoising, and a lightweight temporal-aware decoder with a Temporal Processor Module (TPM) to enhance detail and temporal coherence. Unlike chunk-wise streaming inference, our strictly frame-by-frame causal design avoids sequence-level waiting, substantially reducing time-to-first-frame and end-to-end latency. Stream-DiffVSR processes 720p frames in 0.328 seconds on an RTX 4090 and consistently outperforms prior diffusion-based baselines. Compared with the online state-of-the-art TMP, it improves perceptual quality (LPIPS +0.095). Compared with prior diffusion-based VSR methods such as MGLD-VSR, it reduces per-frame runtime by over 130x. Moreover, Stream-DiffVSR substantially lowers time-to-first-frame for diffusion-based VSR, reducing initial delay from over 4600 seconds to 0.328 seconds, making diffusion-based VSR markedly more practical for low-latency online and streaming deployment. Project page: https://jamichss.github.io/stream-diffvsr-project-page/
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。
