Self2Seg: Single-Image Self-Supervised Joint Segmentation and Denoising

arXiv:2309.10511v2 Announce Type: replace-cross
Abstract: We develop Self2Seg, a self-supervised method for the joint segmentation and denoising of a single image. To this end, we combine the advantages of variational segmentation with self-supervised deep learning. One major benefit of our method lies in the fact, that in contrast to data-driven methods, where huge amounts of labeled samples are necessary, Self2Seg segments an image into meaningful regions without any training database. Moreover, we demonstrate that self-supervised denoising itself is significantly improved …

abstract advantages arxiv benefit contrast cs.cv cs.lg data data-driven deep learning denoising image lies major math.oc segmentation type