用条件扩散模型学习运动-外观耦合先验求解视频逆问题

该方法不同于常见的做法——以往多依赖光度损失或基于 warping 的时间一致性约束，这些方法隐含假设帧间变化完全由运动解释，在遮挡、光照变化和非刚性形变场景下会失效。新提出的是运动-外观先验作为即插即用正则项，保留了预训练图像扩散模型的优势，兼容已有外观正则化技术。

在动态视频逆问题实验中，学习到的运动-外观耦合先验在重建效果上超过光度一致性和噪声 warping 基线，并且可以迁移到心脏 MRI 重建任务。

Learning Motion-Appearance Coupling Priors for Solving Video Inverse Problems

Reconstructing video from degraded measurements requires priors that capture both frame appearance and temporal dynamics. Many recent approaches combine pretrained image diffusion priors with motion guidance, sidestepping the costs of training large video models. Temporal consistency is often enforced via photometric losses or warping-based constraints, which implicitly assume that motion explains frame-to-frame or latent-to-latent changes up to small deviations, an assumption that fails under occlusions, lighting changes, and non-rigid deformation. In this paper, we propose to learn the coupling between motion and frame appearance as a generative prior. We learn the distribution of motion-induced appearance residuals with a conditional diffusion model and use it to regularize reconstruction in video inverse problems. Our motion-appearance prior acts as a plug-in regularizer for diffusion-based video reconstruction, preserving the benefits of image diffusion models while remaining compatible with existing appearance regularization techniques. Experiments on dynamic video inverse problems show that reconstruction with a learnt motion-appearance coupling prior outperforms photometric-consistency and noise-warping baselines, and that the approach also transfers to cardiac MRI reconstruction.

本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：扩散模型、视频重建、逆问题、扩散先验，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明：本文原始线索采编自「arXiv cs.LG」（@Anselm Krainovic, Reinhard Heckel），经 AITOP 多维评分管线结构化提炼。