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

Dongdong Chen, Julián Tachella, Mike E. Davies

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

15 Citations (Scopus)

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
Pages5647-5656
Number of pages10
ISBN (Electronic)9781665469463
DOIs
Publication statusPublished - 27 Sept 2022
Event2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition - New Orleans, United States
Duration: 19 Jun 202224 Jun 2022

Conference

Conference2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Abbreviated titleCVPR 2022
Country/TerritoryUnited States
CityNew Orleans
Period19/06/2224/06/22

Keywords

  • Equivariant Imaging
  • Unsupervised Learning
  • Deep learning
  • image reconstruction

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