Mid Sweden University

miun.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Approximate Maximum a Posteriori Training of Diffusion Models for Image Restoration
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-). Inria Rennes, Rennes, France. (Realistic3D)ORCID iD: 0009-0005-1954-1143
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-). (Realistic3D)ORCID iD: 0000-0003-3751-6089
Inria Rennes, Rennes, France.ORCID iD: 0000-0003-1604-967X
2026 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 14, p. 102614-102634Article in journal (Refereed) Published
Abstract [en]

Inverse problems such as super-resolution, deblurring, and inpainting are commonly solved using iterative Maximum a Posteriori (MAP) solvers with pretrained priors. Recently, Diffusion Models (DMs) have achieved state-of-the-art restoration quality through a generative sampling process conditioned on the degraded observation, leveraging pretrained priors similar to those used in MAP estimation. Motivated by this connection, previous work has trained DMs as deep regularizers in an iterative MAP solver, optimizing them on the mean squared error (MSE) between the estimate and the ground truth. However, MSE trains an estimator to seek the posterior mean rather than the mode, introducing a mismatch with MAP estimation that can result in blurry images. In this work, we present an extended investigation of such MAP training for DMs and introduce a loss designed to address the mismatch, providing a theoretical justification for its use in MAP training. Our experiments show that MAP training with MSE or the proposed loss improves robustness to hyperparameter selection and helps reduce restoration failures in certain cases. Furthermore, we observe that the proposed loss reduces training time and can produce sharper restorations with fewer artifacts when compared to MAP training using MSE. 

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2026. Vol. 14, p. 102614-102634
Keywords [en]
Training, Modeling, Inverse problems, Lamps, Noise reduction, Superresolution, Deblurring, PSNR, Image restoration, Weighted sum model, Deep equilibrium models, diffusion models, image restoration, inverse problems, maximum a posteriori estimation
National Category
Computer Vision and Learning Systems
Identifiers
URN: urn:nbn:se:miun:diva-58204DOI: 10.1109/access.2026.3708219ISI: 001821036400044Scopus ID: 2-s2.0-105043732011OAI: oai:DiVA.org:miun-58204DiVA, id: diva2:2089674
Funder
Interreg Aurora, 20366448Mid Sweden University, 2020/1413Available from: 2026-08-04 Created: 2026-08-04 Last updated: 2026-09-01Bibliographically approved

Open Access in DiVA

LAMP(8064 kB)48 downloads
File information
File name FULLTEXT01.pdfFile size 8064 kBChecksum SHA-512
abed6133785ab6798d4f73acea6823612f202d891dd1480b2d6b4dad156d3f7cb2f116202d40761e8872147f23f065c46a6c141682fb3238471f710492eca8a5
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Willingham, SamuelSjöström, Mårten

Search in DiVA

By author/editor
Willingham, SamuelSjöström, MårtenGuillemot, Christine
By organisation
Department of Computer and Electrical Engineering (2023-)
In the same journal
IEEE Access
Computer Vision and Learning Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 48 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 118 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf