Discriminative Transfer Learning for General Image Restoration

DOI10.1109/TIP.2018.2831925zbMATH Open1409.94672DBLPjournals/tip/XiaoHHSH18arXiv1703.09245WikidataQ57340843 ScholiaQ57340843MaRDI QIDQ4617427

Author name not available (Why is that?)

Publication date: 6 February 2019

Published in: (Search for Journal in Brave)

Abstract: Recently, several discriminative learning approaches have been proposed for effective image restoration, achieving convincing trade-off between image quality and computational efficiency. However, these methods require separate training for each restoration task (e.g., denoising, deblurring, demosaicing) and problem condition (e.g., noise level of input images). This makes it time-consuming and difficult to encompass all tasks and conditions during training. In this paper, we propose a discriminative transfer learning method that incorporates formal proximal optimization and discriminative learning for general image restoration. The method requires a single-pass training and allows for reuse across various problems and conditions while achieving an efficiency comparable to previous discriminative approaches. Furthermore, after being trained, our model can be easily transferred to new likelihood terms to solve untrained tasks, or be combined with existing priors to further improve image restoration quality.

Full work available at URL: https://arxiv.org/abs/1703.09245

Mathematics Subject Classification ID

No records found.

This page was built for publication: Discriminative Transfer Learning for General Image Restoration

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4617427)