Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurements
This addresses the challenge of robust unsupervised imaging for applications like medical imaging and computational photography, where clean signals are hard to obtain, representing an incremental improvement over prior equivariant imaging methods.
The paper tackles the problem of learning to reconstruct images from noisy and partial measurements without clean training data, proposing a Robust Equivariant Imaging (REI) framework that uses Stein's Unbiased Risk Estimator (SURE) to achieve robust unsupervised training, resulting in considerable performance gains on linear and nonlinear inverse problems.
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.