On normalization-equivariance properties of supervised and unsupervised denoising methods: a survey

arXiv:2402.15352v1 Announce Type: cross
Abstract: Image denoising is probably the oldest and still one of the most active research topic in image processing. Many methodological concepts have been introduced in the past decades and have improved performances significantly in recent years, especially with the emergence of convolutional neural networks and supervised deep learning. In this paper, we propose a survey of guided tour of supervised and unsupervised learning methods for image denoising, classifying the main principles elaborated during this evolution, …

abstract arxiv concepts convolutional neural networks cs.cv cs.lg denoising emergence image image processing networks neural networks normalization performances processing research survey type unsupervised