Metraipolis › archive › dc_55ca71a430eb

FlowFPR: Flow Matching Prior for Oversampled Fourier Phase Retrieval — arXiv:2611.00157

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.00157
License (as archived): CC0-1.0
Archived: 2026-11-03T11:24:47.303Z
SHA-256 of the archived text: 0bd2bf10984bcac5cc639ece194ec860cd8b574e4909066d976eed7b75700c33
Stable URL of this page: https://metraipolis.com/documento/dc_55ca71a430eb

How to cite

FlowFPR: Flow Matching Prior for Oversampled Fourier Phase Retrieval — arXiv:2611.00157 — arXiv (en), https://arxiv.org/abs/2611.00157 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_55ca71a430eb (Metraipolis archive dc_55ca71a430eb, sha256 0bd2bf10984bcac5cc639ece194ec860cd8b574e4909066d976eed7b75700c33)

BibTeX

@misc{dc55ca71a430eb,
  title = {FlowFPR: Flow Matching Prior for Oversampled Fourier Phase Retrieval — arXiv:2611.00157},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00157},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_55ca71a430eb; sha256 0bd2bf10984bcac5cc639ece194ec860cd8b574e4909066d976eed7b75700c33},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00157. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Fourier phase retrieval reconstructs images from magnitude measurements without phase information, but noise and channel ambiguities make natural color-image recovery challenging. Although diffusion-prior methods provide strong image constraints, their recovery can deteriorate under stronger measurement noise, and repeated generative updates incur substantial computational cost. This paper proposes FlowFPR, which integrates a pretrained Flow Matching prior with relaxed averaged alternating reflections for oversampled Fourier phase retrieval. Each outer iteration obtains a clean image estimate through a single time-dependent Flow prediction, applies measurement-consistency correction, and reconstructs the next path state after fusing the two candidates. This process requires no backpropagation of measurement errors through the Flow network. To address ineffective or excessive correction caused by prescribed fusion weights and fixed inner depths, we introduce adaptive fusion based on residual improvement and a controlled inner search combining early stopping with best-so-far candidate selection. Their combination yields a joint variant alongside the basic method and the two independent improvements. Experiments on natural face images under a common ground-truth-assisted multiple-restart evaluation protocol show that the joint variant achieves the best mean quality among the evaluated methods at the two tested nonzero noise levels, while same-hardware timing demonstrates lower end-to-end runtime than the diffusion-based baselines.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.00157 — 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 2026-11-03T11:02:37.759Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).