Pith. sign in

REVIEW 1 cited by

Patch-Based Diffusion Models Beat Whole-Image Models for Mismatched Distribution Inverse Problems

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.11730 v1 pith:VS7ZBAKG submitted 2024-10-15 cs.CV cs.AIeess.IV

classification cs.CVcs.AIeess.IV
keywords distributionmodelstestimagepatch-basedtrainingdiffusionfirst
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Diffusion models have achieved excellent success in solving inverse problems due to their ability to learn strong image priors, but existing approaches require a large training dataset of images that should come from the same distribution as the test dataset. When the training and test distributions are mismatched, artifacts and hallucinations can occur in reconstructed images due to the incorrect priors. In this work, we systematically study out of distribution (OOD) problems where a known training distribution is first provided. We first study the setting where only a single measurement obtained from the unknown test distribution is available. Next we study the setting where a very small sample of data belonging to the test distribution is available, and our goal is still to reconstruct an image from a measurement that came from the test distribution. In both settings, we use a patch-based diffusion prior that learns the image distribution solely from patches. Furthermore, in the first setting, we include a self-supervised loss that helps the network output maintain consistency with the measurement. Extensive experiments show that in both settings, the patch-based method can obtain high quality image reconstructions that can outperform whole-image models and can compete with methods that have access to large in-distribution training datasets. Furthermore, we show how whole-image models are prone to memorization and overfitting, leading to artifacts in the reconstructions, while a patch-based model can resolve these issues.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Personalized MR-Informed Diffusion Models for 3D PET Image Reconstruction

    physics.med-ph 2025-06 conditional novelty 6.0 of 10

    Registering other subjects' PET images into a target subject's MR anatomy creates training data that, when used to pre-train a diffusion model, improves low-count PET reconstruction accuracy.

Pith tools