Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurements

Dongdong Chen, Julián Tachella, Michael E. Davies

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Deep networks provide state-of-the-art performance in multiple imaging inverse problems ranging from medical imaging to computational photography. However, most existing networks are trained with clean signals which are often hard or impossible to obtain. Equivariant imaging (EI) is a recent self-supervised learning framework that exploits the group invariance present in signal distributions to learn a reconstruction function from partial measurement data alone. While EI results are impressive, its performance degrades with increasing noise. In this paper, we propose a Robust Equivariant Imaging (REI) framework which can learn to image from noisy partial measurements alone. The proposed method uses Stein's Unbiased Risk Estimator (SURE) to obtain a fully unsupervised training loss that is robust to noise. We show that REI leads to considerable performance gains on linear and nonlinear inverse problems, thereby paving the way for robust unsupervised imaging with deep networks. Code is available at https://github.com/edongdongchen/REI.
Original languageEnglish
Title of host publication2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherIEEE Xplore
Pages5637-5646
ISBN (Electronic)978-1-6654-6946-3
ISBN (Print)978-1-6654-6947-0
DOIs
Publication statusE-pub ahead of print - 27 Sep 2022
EventIEEE/CVF Conference on Computer Vision and Pattern Recognition 2022
- New Orleans, United States
Duration: 19 Jun 202224 Jun 2022
https://cvpr2022.thecvf.com/

Publication series

NameConference on Computer Vision and Pattern Recognition (CVPR)
PublisherIEEE
ISSN (Print)1063-6919
ISSN (Electronic)2575-7075

Conference

ConferenceIEEE/CVF Conference on Computer Vision and Pattern Recognition 2022
Abbreviated titleCVPR 2022
Country/TerritoryUnited States
CityNew Orleans
Period19/06/2224/06/22
Internet address

Keywords

  • Computational photography
  • Low-level vision
  • Medical
  • Optimization methods
  • Physics-based vision and shape-from-X
  • Self- & semi- & meta- & unsupervised learning
  • biological and cell microscopy

Fingerprint

Dive into the research topics of 'Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurements'. Together they form a unique fingerprint.

Cite this