Investigating the Feasibility of Patch-based Inference for Generalized Diffusion Priors in Inverse Problems for Medical Images

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Roy, Saikat, Mostapha, Mahmoud, Miron, Radu, Holbrook, Matt, Nadar, Mariappan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909595324121088
author Roy, Saikat
Mostapha, Mahmoud
Miron, Radu
Holbrook, Matt
Nadar, Mariappan
author_facet Roy, Saikat
Mostapha, Mahmoud
Miron, Radu
Holbrook, Matt
Nadar, Mariappan
contents Plug-and-play approaches to solving inverse problems such as restoration and super-resolution have recently benefited from Diffusion-based generative priors for natural as well as medical images. However, solutions often use the standard albeit computationally intensive route of training and inferring with the whole image on the diffusion prior. While patch-based approaches to evaluating diffusion priors in plug-and-play methods have received some interest, they remain an open area of study. In this work, we explore the feasibility of the usage of patches for training and inference of a diffusion prior on MRI images. We explore the minor adaptation necessary for artifact avoidance, the performance and the efficiency of memory usage of patch-based methods as well as the adaptability of whole image training to patch-based evaluation - evaluating across multiple plug-and-play methods, tasks and datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2501_15309
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Investigating the Feasibility of Patch-based Inference for Generalized Diffusion Priors in Inverse Problems for Medical Images
Roy, Saikat
Mostapha, Mahmoud
Miron, Radu
Holbrook, Matt
Nadar, Mariappan
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Plug-and-play approaches to solving inverse problems such as restoration and super-resolution have recently benefited from Diffusion-based generative priors for natural as well as medical images. However, solutions often use the standard albeit computationally intensive route of training and inferring with the whole image on the diffusion prior. While patch-based approaches to evaluating diffusion priors in plug-and-play methods have received some interest, they remain an open area of study. In this work, we explore the feasibility of the usage of patches for training and inference of a diffusion prior on MRI images. We explore the minor adaptation necessary for artifact avoidance, the performance and the efficiency of memory usage of patch-based methods as well as the adaptability of whole image training to patch-based evaluation - evaluating across multiple plug-and-play methods, tasks and datasets.
title Investigating the Feasibility of Patch-based Inference for Generalized Diffusion Priors in Inverse Problems for Medical Images
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2501.15309