Metraipolis › archive › dc_bb82b46c604b

Frozen CLIP Priors for Robust Self-Supervised Poisson Inverse Problems — arXiv:2608.20524

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20524
License (as archived)
CC0-1.0
Archived
2026-10-18T10:56:29.154Z
SHA-256 of the archived text
ec66b20c2094e5edc4023c81199a0282ac3022abc872c040e0ae247d31b67faf
Stable URL of this page
https://metraipolis.com/documento/dc_bb82b46c604b

How to cite

Frozen CLIP Priors for Robust Self-Supervised Poisson Inverse Problems — arXiv:2608.20524 — arXiv (en), https://arxiv.org/abs/2608.20524 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb82b46c604b (Metraipolis archive dc_bb82b46c604b, sha256 ec66b20c2094e5edc4023c81199a0282ac3022abc872c040e0ae247d31b67faf)
BibTeX
@misc{dcbb82b46c604b,
  title = {Frozen CLIP Priors for Robust Self-Supervised Poisson Inverse Problems — arXiv:2608.20524},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20524},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb82b46c604b; sha256 ec66b20c2094e5edc4023c81199a0282ac3022abc872c040e0ae247d31b67faf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20524. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Self-supervised learning for imaging inverse problems is increasingly important in photon-limited settings, where acquiring clean ground truth is impractical and reconstruction must remain stable under dataset and acquisition shifts. This challenge is amplified under Poisson noise, whose signal-dependent statistics interact with sampling operators (e.g., CFA mosaicing). Meanwhile, foundation vision encoders trained at web scale offer distortion-invariant, content-related representations that generalize well across domains, suggesting a promising route to build priors that transfer beyond the training distribution without expensive fine-tuning. This paper proposes an ADMM-inspired unrolled plug-and-play solver for Poisson inverse problems that decouples a closed-form data-consistency update from a parameter-efficient prior. The prior is implemented as a lightweight decoder operating on frozen CLIP RN50 dense multi-scale features, adapting foundation representations with less trainable parameters. For self-supervision, the method integrates GR2R measurement-domain re-corruption with an Equivariant Imaging regularizer via virtual acquisitions. Experiments on Poisson CFA demosaicing and deblurring show competitive quality, improved robustness under shifts, and self-supervised performance approaching supervised training.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-24 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/2608.20524 — 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 2026-10-18T10:48:13.616Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).