Fast Equivariant Imaging: Acceleration for Unsupervised Learning via Augmented Lagrangian and Auxiliary PnP Denoisers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Guixian, Li, Jinglai, Tang, Junqi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912942353547264
author Xu, Guixian
Li, Jinglai
Tang, Junqi
author_facet Xu, Guixian
Li, Jinglai
Tang, Junqi
contents In this work, we propose Fast Equivariant Imaging (FEI), a novel unsupervised learning framework to rapidly and efficiently train deep imaging networks without ground-truth data. From the perspective of reformulating the Equivariant Imaging based optimization problem via the method of Lagrange multipliers and utilizing plug-and-play denoisers, this novel unsupervised scheme shows superior efficiency and performance compared to the vanilla Equivariant Imaging paradigm. In particular, our FEI schemes achieve an order-of-magnitude (10x) acceleration over standard EI on training U-Net for X-ray CT reconstruction and image inpainting, with improved generalization performance. In addition, the proposed scheme enables efficient test-time adaptation of a pretrained model to individual samples to secure further performance improvements. Extensive experiments show that the proposed approach provides a noticeable efficiency and performance gain over existing unsupervised methods and model adaptation techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2507_06764
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fast Equivariant Imaging: Acceleration for Unsupervised Learning via Augmented Lagrangian and Auxiliary PnP Denoisers
Xu, Guixian
Li, Jinglai
Tang, Junqi
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Optimization and Control
In this work, we propose Fast Equivariant Imaging (FEI), a novel unsupervised learning framework to rapidly and efficiently train deep imaging networks without ground-truth data. From the perspective of reformulating the Equivariant Imaging based optimization problem via the method of Lagrange multipliers and utilizing plug-and-play denoisers, this novel unsupervised scheme shows superior efficiency and performance compared to the vanilla Equivariant Imaging paradigm. In particular, our FEI schemes achieve an order-of-magnitude (10x) acceleration over standard EI on training U-Net for X-ray CT reconstruction and image inpainting, with improved generalization performance. In addition, the proposed scheme enables efficient test-time adaptation of a pretrained model to individual samples to secure further performance improvements. Extensive experiments show that the proposed approach provides a noticeable efficiency and performance gain over existing unsupervised methods and model adaptation techniques.
title Fast Equivariant Imaging: Acceleration for Unsupervised Learning via Augmented Lagrangian and Auxiliary PnP Denoisers
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Optimization and Control
url https://arxiv.org/abs/2507.06764