AutoRefiner: 通过在随机采样路径上的反思细化改进自回归视频扩散模型
AutoRefiner: Improving Autoregressive Video Diffusion Models via Reflective Refinement Over the Stochastic Sampling Path
AI总结：
AutoRefiner通过路径噪声细化和反射式KV缓存改进AR-VDMs的样本保真度
摘要：
自回归视频扩散模型（AR-VDMs）显示出作为双向VDMs的可扩展替代方案的强劲前景，能够实现实时和交互式应用。然而，其样本保真度仍有改进的空间。一个有前景的解决方案是推理时对齐，通过优化噪声空间来提高样本保真度，而无需更新模型参数。然而，基于优化或搜索的方法对于AR-VDMs来说计算上是不现实的。最近的文本到图像（T2I）工作通过前馈噪声细化器来解决这个问题，这些细化器在单次正向传递中调节采样的噪声。这种噪声细化器能否扩展到AR-VDMs？我们发现直接将T2I噪声细化器扩展到AR-VDMs的失败，并提出AutoRefiner——一个针对AR-VDMs设计的噪声细化器，具有两个关键设计：路径噪声细化和反射式KV缓存。实验表明，AutoRefiner为AR-VDMs提供了一个高效的插件，通过在随机去噪路径上细化噪声，有效提高了样本保真度。
英文摘要：
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.
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。
