Metraipolis › archive › dc_7c83f611b2fc

Image Reconstruction from Phase with Untrained Neural Priors — arXiv:2609.30659

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30659
License (as archived)
CC0-1.0
Archived
2026-10-08T03:12:53.560Z
SHA-256 of the archived text
5829bef5b8dcf0c6f6152586c3aab4c72547d1bf5f758cad574296d2a3404caf
Stable URL of this page
https://metraipolis.com/documento/dc_7c83f611b2fc

How to cite

Image Reconstruction from Phase with Untrained Neural Priors — arXiv:2609.30659 — arXiv (en), https://arxiv.org/abs/2609.30659 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7c83f611b2fc (Metraipolis archive dc_7c83f611b2fc, sha256 5829bef5b8dcf0c6f6152586c3aab4c72547d1bf5f758cad574296d2a3404caf)
BibTeX
@misc{dc7c83f611b2fc,
  title = {Image Reconstruction from Phase with Untrained Neural Priors — arXiv:2609.30659},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30659},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7c83f611b2fc; sha256 5829bef5b8dcf0c6f6152586c3aab4c72547d1bf5f758cad574296d2a3404caf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30659. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Fourier phase encodes important spatial image structure, but recovering an image without measured spectral magnitude requires additional constraints and leaves absolute intensity ambiguous. We propose a projection-based two-stage framework that combines Fourier-phase and spatial-support constraints with an image-specific neural prior. The first stage alternates constraint enforcement with regularized neural-prior updates, while the second performs phase/support refinement alone with guaranteed convergence. We evaluate two neural-prior implementations on the same 77 microscopy images and compare them with a constraint-only baseline. After 500 final refinement passes, the best-performing variant achieves 31.41 dB pooled PSNR, 35.75 dB mean PSNR, and 0.9531 mean SSIM, improving pooled PSNR by 1.51~dB and reducing pooled MSE by 29.3% relative to the baseline. The results demonstrate the benefit of combining neural guidance with explicit constraint refinement at the evaluated iteration budget, while showing that lower phase residual alone does not guarantee greater reconstruction accuracy.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.CV).
Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.30659 — 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 2026-10-08T02:50:19.141Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).