ReBridge-Flow：用于图像修复的流匹配中后验桥的重新耦合
ReBridge-Flow: Re-Coupling Posterior Bridges in Flow Matching for Image Restoration
浏览论文内容
中文总结 AI 辅助
针对现有流匹配图像修复方法中局部修正破坏端点耦合的问题，提出ReBridge-Flow后验桥重新耦合方法，通过干净侧锚定与源端点重新耦合提升桥兼容性，实验证实其可缓解桥不匹配并增强修复图像的结构一致性。
中文摘要 AI 辅助
流匹配通过学习源分布与数据分布之间的连续传输，为图像修复提供了一种高效的生成先验。然而，现有方法通常通过局部修正来引入测量约束，此类修正可能会破坏预训练流隐式编码的源-干净端点耦合，导致修正后的端点对与当前状态不兼容。为解决该问题，我们提出ReBridge-Flow，一种后验桥重新耦合方法。具体而言，给定当前状态，ReBridge-Flow首先解码对应的局部源端点与干净端点，随后通过干净侧锚定引入测量信息，并同步重新耦合源端点，得到具备测量感知、局部桥兼容性提升的端点对。重新耦合的端点进一步定义了后验感知的传输方向，以推进采样过程。我们还提出后验桥缺陷，其共同表征测量误差、与流先验的偏差以及桥不匹配，为干净侧锚定和源侧重新耦合提供显式更新依据。在多个自然图像与医学图像修复任务上开展的大量实验表明，ReBridge-Flow可有效缓解桥不匹配问题，提升修复图像的结构一致性。
英文摘要
Flow Matching provides an efficient generative prior for image restoration by learning continuous transport between source and data distributions. However, existing methods typically incorporate measurement constraints through local corrections. Such corrections may disrupt the source-clean endpoint coupling implicitly encoded by the pretrained flow, making the corrected endpoint pair incompatible with the current state. To address this issue, we propose ReBridge-Flow, a posterior bridge re-coupling method. Specifically, given the current state, ReBridge-Flow first decodes the corresponding local source and clean endpoints. It then incorporates measurement information through clean-side anchoring and synchronously re-couples the source endpoint, yielding a measurement-aware endpoint pair with improved local bridge compatibility. The re-coupled endpoints further define a posterior-informed transport direction for advancing the sampling process. We also introduce the Posterior Bridge Defect, which jointly characterizes measurement error, deviation from the flow prior, and bridge mismatch, and leads to explicit updates for clean-side anchoring and source-side re-coupling. Extensive experiments on multiple natural and medical image restoration tasks demonstrate that ReBridge-Flow effectively alleviates bridge mismatch and improves the structural consistency of restored images.
发表机构
- Jiangsu University（江苏大学）
- Griffith University（格里菲斯大学）
- Sichuan University（四川大学）
- University of Malaya（马来亚大学）
- University of Science and Technology of China（中国科学技术大学）
- Tianjin University（天津大学）
- University of Southern Queensland（南昆士兰大学）
- Southern University of Science and Technology（南方科技大学）
机构由 AI 辅助整理，请以论文原文为准。
