Metraipolis › archive › dc_3f305cde2bae
ReBridge-Flow: Re-Coupling Posterior Bridges in Flow Matching for Image Restoration — arXiv:2609.00811
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00811
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:13:37.690Z
- SHA-256 of the archived text
cbb61c7cae88bcfdc5b2ca78d4a03d7e881291fbe82cb83dc6506d234f1ea12d- Stable URL of this page
https://metraipolis.com/documento/dc_3f305cde2bae
How to cite
ReBridge-Flow: Re-Coupling Posterior Bridges in Flow Matching for Image Restoration — arXiv:2609.00811 — arXiv (en), https://arxiv.org/abs/2609.00811 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3f305cde2bae (Metraipolis archive dc_3f305cde2bae, sha256 cbb61c7cae88bcfdc5b2ca78d4a03d7e881291fbe82cb83dc6506d234f1ea12d)
BibTeX
@misc{dc3f305cde2bae,
title = {ReBridge-Flow: Re-Coupling Posterior Bridges in Flow Matching for Image Restoration — arXiv:2609.00811},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00811},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3f305cde2bae; sha256 cbb61c7cae88bcfdc5b2ca78d4a03d7e881291fbe82cb83dc6506d234f1ea12d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00811. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.00811 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T07:00:58.933Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).