Probabilistic Residual Learning for Aleatoric Uncertainty in Image Restoration

Understand

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.