STeP：利用时空扩散先验解决科学视频逆问题的框架
STeP: A Framework for Solving Scientific Video Inverse Problems with Spatiotemporal Diffusion Priors
AI总结：
本文提出STeP即插即用框架，通过学习时空扩散先验从稀疏时变测量中重建科学视频，并在黑洞视频与动态MRI任务上显著提升时空结构恢复效果。
摘要：
从随时间变化的测量中重建具有空间和时间一致性的视频，是许多科学领域的一项基本挑战。一个主要困难来自测量的稀疏性，这会阻碍对时间动态的准确恢复。现有基于图像扩散的方法依赖于直接从测量中提取时间一致性，因此在具有高时空不确定性的科学任务上效果受限。我们通过提出一种即插即用框架来解决这一困难，该框架融合了学习到的时空扩散先验。由于其即插即用特性，我们的框架能够灵活应用于不同的视频逆问题，而无需针对任务的专门设计和时间启发式方法。我们进一步证明，时空扩散模型可以利用有限的视频数据进行高效训练。我们在两个具有挑战性的科学视频重建任务上验证了该方法：黑洞视频重建和动态 MRI。当基线方法难以给出时间一致的重建结果时，我们的方法在恢复底层真实视频的时空结构方面取得了显著提升。
英文摘要：
Reconstructing spatially and temporally coherent videos from time-varying measurements is a fundamental challenge in many scientific domains. A major difficulty arises from the sparsity of measurements, which hinders accurate recovery of temporal dynamics. Existing image diffusion-based methods rely on extracting temporal consistency directly from measurements, limiting their effectiveness on scientific tasks with high spatiotemporal uncertainty. We address this difficulty by proposing a plug-and-play framework that incorporates a learned spatiotemporal diffusion prior. Due to its plug-and-play nature, our framework can be flexibly applied to different video inverse problems without the need for task-specific design and temporal heuristics. We further demonstrate that a spatiotemporal diffusion model can be trained efficiently with limited video data. We validate our approach on two challenging scientific video reconstruction tasks: black hole video reconstruction and dynamic MRI. While baseline methods struggle to provide temporally coherent reconstructions, our approach achieves significantly improved recovery of the spatiotemporal structure of the underlying ground truth videos.
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。
