让自回归视频扩散模型生成更清晰视频，只需一次轻量级优化
AutoRefiner: Improving Autoregressive Video Diffusion Models via Reflective Refinement Over the Stochastic Sampling Path
- 在采样路径上动态修正噪声，不改动模型参数
- 比原模型生成视频质量显著提升，且推理速度不受影响
- 适合需要高质量实时视频生成的开发者使用
自回归视频扩散模型（AR-VDMs）作为可扩展的替代方案，具备实时与交互应用潜力，但样本保真度仍有提升空间。一种有前景的方案是推理时对齐，通过优化噪声空间提升样本质量而无需更新模型参数。然而，基于优化或搜索的方法对AR-VDMs计算开销过大。近期文本到图像（T2I）工作采用前馈噪声修正器，在单次前向传播中调节采样噪声。能否将此类修正器扩展至AR-VDMs？我们发现直接延用T2I方法在AR-VDMs上会失效。为此，提出专为AR-VDMs设计的AutoRefiner，包含两项关键设计：路径噪声精修与反射式键值缓存（reflective KV-cache）。实验表明，AutoRefiner可作为高效插件集成于AR-VDMs，通过沿随机去噪路径精修噪声，显著提升生成样本保真度。
原文摘要 · Abstract (English)
Autoregressive video diffusion models (AR-VDMs) show strong promise as scalable alternatives to bidirectional VDMs, enabling real-time and interactive applications. Yet there remains room for improvement in their sample fidelity. A promising solution is inference-time alignment, which optimizes the noise space to improve sample fidelity without updating model parameters. Yet, optimization- or search-based methods are computationally impractical for AR-VDMs. Recent text-to-image (T2I) works address this via feedforward noise refiners that modulate sampled noises in a single forward pass. Can such noise refiners be extended to AR-VDMs? We identify the failure of naively extending T2I noise refiners to AR-VDMs and propose AutoRefiner-a noise refiner tailored for AR-VDMs, with two key designs: pathwise noise refinement and a reflective KV-cache. Experiments demonstrate that AutoRefiner serves as an efficient plug-in for AR-VDMs, effectively enhancing sample fidelity by refining noise along stochastic denoising paths.
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。