ReBridge-Flow: Re-Coupling Posterior Bridges in Flow Matching for Image Restoration

2026-09-01

AI Summary

为解决图像恢复中测量约束导致的源-清洁端点耦合破坏问题，提出ReBridge-Flow方法，通过重新耦合后验桥并引入后验桥缺陷来改进局部桥兼容性和恢复图像的一致性。

Abstract

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.

Problem

• Flow Matching
• Image Restoration
• Measurement Constraints
• Endpoint Coupling

Innovation

• ReBridge-Flow
• Posterior Bridge Re-coupling
• Image Restoration
• Posterior Bridge Defect
• Measurement-aware Endpoint Pair