Metraipolis › archive › dc_cd5f78bd794f

FIRM: Flow-based Imaging via Regularized Minimization — arXiv:2609.12953

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12953
License (as archived)
CC0-1.0
Archived
2026-10-16T03:57:51.222Z
SHA-256 of the archived text
3dccf3af19a5e887ee8746e76baf03cc37e00e98db0195729aaa2d41f825ca2e
Stable URL of this page
https://metraipolis.com/documento/dc_cd5f78bd794f

How to cite

FIRM: Flow-based Imaging via Regularized Minimization — arXiv:2609.12953 — arXiv (en), https://arxiv.org/abs/2609.12953 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd5f78bd794f (Metraipolis archive dc_cd5f78bd794f, sha256 3dccf3af19a5e887ee8746e76baf03cc37e00e98db0195729aaa2d41f825ca2e)
BibTeX
@misc{dccd5f78bd794f,
  title = {FIRM: Flow-based Imaging via Regularized Minimization — arXiv:2609.12953},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12953},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd5f78bd794f; sha256 3dccf3af19a5e887ee8746e76baf03cc37e00e98db0195729aaa2d41f825ca2e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12953. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Flow matching methods for imaging inverse problems typically incorporate measurements through network conditioning or guidance during sampling. Neither approach explicitly applies the forward operator within the learned conditional velocity field. We develop a principled measurement-conditional velocity parameterization that does. For a linear interpolation path, we express the optimal velocity through the posterior mean $E[x_1|x_t, y]$ and show that this mean is the unique minimizer of a variational objective with an explicit data-consistency term. The velocity defined by this minimizer provably transports the source distribution to the measurement-conditioned posterior. This result leads to a forward operator-aware velocity field that is trained end-to-end and requires no separate guidance during sampling. Across five imaging tasks, our method achieves leading reconstruction quality with up to $50\times$ fewer network evaluations than competitive flow-based methods. Varying the number of sampling steps also controls the distortion-perception trade-off without retraining.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-14 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.12953 — 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 2026-10-16T03:44:26.330Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).