LIRA: Lifelong Image Restoration from Unknown Blended Distortions

Liu, Jianzhao, Lin, Jianxin, Li, Xin, Zhou, Wei, Liu, Sen and Chen, Zhibo 2020. LIRA: Lifelong Image Restoration from Unknown Blended Distortions. Presented at: 16th European Conference on Computer Vision (ECCV 2020), Glasgow, Scotland, 23-28 August 2020. Published in: Vedaldi, Andrea, Bischof, Horst, Brox, Thomas and Frahm, Jan-Michael eds. Computer Vision – ECCV 2020. Lecture Notes in Computer Science. Lecture Notes in Computer Science Springer International Publishing, pp. 616-632. 10.1007/978-3-030-58523-5_36

Full text not available from this repository.

Abstract

Most existing image restoration networks are designed in a disposable way and catastrophically forget previously learned distortions when trained on a new distortion removal task. To alleviate this problem, we raise the novel lifelong image restoration problem for blended distortions. We first design a base fork-join model in which multiple pre-trained expert models specializing in individual distortion removal task work cooperatively and adaptively to handle blended distortions. When the input is degraded by a new distortion, inspired by adult neurogenesis in human memory system, we develop a neural growing strategy where the previously trained model can incorporate a new expert branch and continually accumulate new knowledge without interfering with learned knowledge. Experimental results show that the proposed approach can not only achieve state-of-the-art performance on blended distortions removal tasks in both PSNR/SSIM metrics, but also maintain old expertise while learning new restoration tasks.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Springer International Publishing
ISBN:	978-3-030-58522-8
ISSN:	0302-9743
Last Modified:	29 Aug 2023 15:30
URI:	https://orca.cardiff.ac.uk/id/eprint/161672

Actions (repository staff only)

Edit Item