Please use this identifier to cite or link to this item:
Title: Exploiting non-local priors via self-convolution for highly-efficient image restoration
Authors: Guo, Lanqing
Zha, Zhiyuan
Ravishankar, Saiprasad
Wen, Bihan
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2022
Source: Guo, L., Zha, Z., Ravishankar, S. & Wen, B. (2022). Exploiting non-local priors via self-convolution for highly-efficient image restoration. IEEE Transactions On Image Processing, 31, 1311-1324.
Project: RG137/20
Journal: IEEE Transactions on Image Processing
Abstract: Constructing effective priors is critical to solving ill-posed inverse problems in image processing and computational imaging. Recent works focused on exploiting non-local similarity by grouping similar patches for image modeling, and demonstrated state-of-the-art results in many image restoration applications. However, compared to classic methods based on filtering or sparsity, non-local algorithms are more time-consuming, mainly due to the highly inefficient block matching step, i.e., distance between every pair of overlapping patches needs to be computed. In this work, we propose a novel Self-Convolution operator to exploit image non-local properties in a unified framework. We prove that the proposed Self-Convolution based formulation can generalize the commonly-used non-local modeling methods, as well as produce results equivalent to standard methods, but with much cheaper computation. Furthermore, by applying Self-Convolution, we propose an effective multi-modality image restoration scheme, which is much more efficient than conventional block matching for non-local modeling. Experimental results demonstrate that (1) Self-Convolution with fast Fourier transform implementation can significantly speed up most of the popular non-local image restoration algorithms, with two-fold to nine-fold faster block matching, and (2) the proposed online multi-modality image restoration scheme achieves superior denoising results than competing methods in both efficiency and effectiveness on RGB-NIR images. The code for this work is publicly available at
ISSN: 1057-7149
DOI: 10.1109/TIP.2022.3140918
Rights: © 2022 IEEE. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles

Citations 50

Updated on Nov 29, 2022

Web of ScienceTM
Citations 50

Updated on Nov 28, 2022

Page view(s)

Updated on Dec 3, 2022

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.