PS-SR：基于投机扩散的伪单步视频超分辨率
PS-SR: Pseudo-Single-Step Video Super-Resolution via Speculative Diffusion
把「单步扩散 + 轻量草稿模型投机式精修」的非对称采样流程用于视频超分，并用频域更新规则把精修限制在高频注入上，为少步扩散复原提供了一条兼顾速度与细节的可复用思路。
原文依据 a lightweight draft model, directly augmented by the base model's features, speculatively performs subsequent refinements
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视频超分辨率（VSR）始终受制于一个关键权衡：单步模型效率无可匹敌，却往往缺乏多步扩散模型所具有的高频细节、创造性与视觉质量，而后者在计算上代价高昂，难以实际应用。本文提出 PS-SR，一种新颖的「伪」单步 VSR 框架，通过计算上非对称的采样流程超越这一权衡。PS-SR 的关键在于其投机扩散机制：一个强大的基模型只执行一次全面的采样步骤，确立全局结构与内容保真度，随后由一个轻量草稿模型在基模型特征的直接增强下，投机式地执行后续精修。关键在于，我们进一步施加频域更新规则，将这些精修约束为仅注入高频细节，从而保留基础的低频内容，并防止采样步骤之间出现语义漂移。由此，PS-SR 营造出单步模型的「错觉」——提供相近的推理速度与输入输出内容一致性——同时获得通常只有昂贵多步生成模型才具备的视觉丰富性与创造性。我们证明，这种「伪单步」范式在速度与单步模型相当的同时达到了最优质量，为实时、高保真视频增强开辟了道路。更多结果请参见项目主页：https://waq2001.github.io/PS-SR-page/。
英文原文摘要 1577 字符
Video Super-Resolution (VSR) fundamentally struggles with a critical trade-off: single-step models offer unmatched efficiency but often lack the high-frequency detail, creativity, and visual quality of their multi-step diffusion counterparts, which are computationally prohibitive for practical use. In this paper, we propose PS-SR, a novel "pseudo" single-step VSR framework that transcends this trade-off through a computationally asymmetric sampling pipeline. The key to PS-SR lies in its speculative diffusion mechanism: a powerful base model performs only a single, comprehensive sampling step, establishing the global structure and content fidelity, after which a lightweight draft model, directly augmented by the base model's features, speculatively performs subsequent refinements. Crucially, we further enforce a frequency-domain update rule that constrains these refinements to exclusively inject high-frequency details, preserving the foundational low-frequency content and preventing semantic drift across sampling steps. By doing so, PS-SR creates the "illusion" of a single-step model--delivering the similar inference speeds and input-output content consistency--while achieving the visual richness and creativity typically reserved for costly multi-step generative models. We demonstrate that our "pseudo-single-step" paradigm achieves state-of-the-art quality with a comparable speed to single-step models, paving the way for real-time, high-fidelity video enhancement. Please refer to our project page for more results: https://waq2001.github.io/PS-SR-page/.