Metraipolis › archive › dc_7fd19167119e

ANaLOG: Anisotropic Native-Latent Operator Guidance for Solving Inverse Problems — arXiv:2609.31933

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31933
License (as archived)
CC0-1.0
Archived
2026-10-07T23:55:02.946Z
SHA-256 of the archived text
ab0d1fe81da8d56d079e02c0d6dbf6beadb2b14f6d5bd8e4361a05f6c294ae28
Stable URL of this page
https://metraipolis.com/documento/dc_7fd19167119e

How to cite

ANaLOG: Anisotropic Native-Latent Operator Guidance for Solving Inverse Problems — arXiv:2609.31933 — arXiv (en), https://arxiv.org/abs/2609.31933 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7fd19167119e (Metraipolis archive dc_7fd19167119e, sha256 ab0d1fe81da8d56d079e02c0d6dbf6beadb2b14f6d5bd8e4361a05f6c294ae28)
BibTeX
@misc{dc7fd19167119e,
  title = {ANaLOG: Anisotropic Native-Latent Operator Guidance for Solving Inverse Problems — arXiv:2609.31933},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31933},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7fd19167119e; sha256 ab0d1fe81da8d56d079e02c0d6dbf6beadb2b14f6d5bd8e4361a05f6c294ae28},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31933. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Native-latent guidance is a recent paradigm for solving inverse problems with latent diffusion models. It replaces repeated evaluations of the image-space forward model, each requiring a decoder pass, with efficient guidance computed using a learned latent-space surrogate. However, existing methods apply guidance uniformly across latent dimensions, ignoring that measurements are informative only along certain directions and that the reliability of model predictions varies across inputs and timesteps. We propose ANaLOG, a framework for efficient uncertainty-aware guidance with pretrained latent diffusion models. ANaLOG models uncertainty by learning an anisotropic, input- and time-dependent covariance that is integrated into the guidance mechanism to emphasize reliable directions and downweight uncertain ones. We theoretically analyze this framework in a linear model setting and prove that anisotropic, uncertainty-aware weighting is necessary for correct sampling, whereas isotropic guidance induces sampling errors. Experiments across five challenging inverse problems show that ANaLOG improves perceptual reconstruction quality over existing methods while preserving efficiency.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 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/2609.31933 — 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 2026-10-07T23:29:27.662Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).