Image Deconvolution via Noise-Tolerant Self-Supervised Inversion

Abstract

We propose a general framework for solving inverse problems in the presence of noise that requires no signal prior, no noise estimate, and no clean training data. We only require that the forward model be available and that the noise be statistically independent across measurement dimensions. We build upon the theory of $\mathcal{J}$-invariant functions (Batson & Royer 2019, arXiv:1901.11365) and show how self-supervised denoising \emph{à la} Noise2Self is a special case of learning a noise-tolerant pseudo-inverse of the identity. We demonstrate our approach by showing how a convolutional neural network can be taught in a self-supervised manner to deconvolve images and surpass in image quality classical inversion schemes such as Lucy-Richardson deconvolution.

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Momentum Contrast for Unsupervised Visual Representation Learning
• How much data is needed to train a medical image deep learning system to achieve necessary high accuracy?
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Learning to Invert: Signal Recovery via Deep Convolutional Networks

Cited by in corpus (1)

• RRLFSOR: An Efficient Self-Supervised Learning Strategy of Graph Convolutional Networks