CONVERGENT PLUG-AND-PLAY USING CONTRACTIVE DENOISERS

Nair, P and Chaudhury, KN (2024) CONVERGENT PLUG-AND-PLAY USING CONTRACTIVE DENOISERS. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024, 14 -19 April 2024, Seoul, pp. 6910-6914.

PDF iee_int_con_aco_spe._sig._pro._pro._2024.2.pdf - Published Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

Plug-and-Play (PnP) algorithms leverage the power of modern denoisers for image reconstruction. They have been shown to deliver state-of-the-art reconstructions using CNN denoisers. It was established in recent works that convergence of these iterative algorithms can be guaranteed using nonexpansive denoisers. However, integrating nonexpansivity into gradient-based learning is challenging. Existing algorithms for training nonexpansive denoisers often cannot guarantee nonexpansivity or are computationally intensive. The present work is based on the observation that the convergence of PnP-FBS and PnP-BBS (PnP based on Forward-Backward and Backward-Backward Splittings) can be guaranteed using contractive denoisers. In this regard, we show that by unfolding FBS iterations applied to wavelet denoising, we can construct contractive image denoisers whose regularization capacity is comparable to CNN denoisers. To the best of knowledge, this is the first work to introduce a simple framework for training denoisers that are provably contractive. © 2024 IEEE.

Item Type:	Conference Paper
Publication:	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to Institute of Electrical and Electronics Engineers Inc.
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	19 Aug 2024 10:56
Last Modified:	19 Aug 2024 10:56
URI:	http://eprints.iisc.ac.in/id/eprint/85473

Actions (login required)

View Item