Probabilistic Residual Learning for Aleatoric Uncertainty in Image Restoration

Abstract

Aleatoric uncertainty is an intrinsic property of ill-posed inverse and imaging problems. Its quantification is vital for assessing the reliability of relevant point estimates. In this paper, we propose an efficient framework for quantifying aleatoric uncertainty for deep residual learning and showcase its significant potential on image restoration. In the framework, we divide the conditional probability modeling for the residual variable into a deterministic homo-dimensional level, a stochastic low-dimensional level and a merging level. The low-dimensionality is especially suitable for sparse correlation between image pixels, enables efficient sampling for high dimensional problems and acts as a regularizer for the distribution. Preliminary numerical experiments show that the proposed method can give not only state-of-the-art point estimates of image restoration but also useful associated uncertainty information.

arXiv commentthis version is outdated, and we are completely reorganizing the paper and split it into several different pieces of work. Thus, we prefer to withdraw it from arxiv

References in corpus (13)

• Auto-Encoding Variational Bayes
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Conditional Generative Adversarial Nets
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Expectation Propagation for approximate Bayesian inference
• Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
• Learned D-AMP: Principled Neural Network based Compressive Image Recovery
• Deep AutoRegressive Networks
• Noise Contrastive Priors for Functional Uncertainty
• Generative Neural Machine Translation
• Variational Gaussian Approximation for Poisson Data
• Expectation Propagation for Poisson Data

Cited by in corpus (5)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Variational Inference for Computational Imaging Inverse Problems
• Quantifying Sources of Uncertainty in Deep Learning-Based Image Reconstruction
• Conditional Variational Autoencoder for Learned Image Reconstruction
• Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descent