Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/162130
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. https://dx.doi.org/10.1109/TIP.2022.3140918
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 https://github.com/GuoLanqing/Self-Convolution.
URI: https://hdl.handle.net/10356/162130
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

SCOPUSTM   
Citations 50

1
Updated on Nov 29, 2022

Web of ScienceTM
Citations 50

1
Updated on Nov 28, 2022

Page view(s)

7
Updated on Dec 3, 2022

Google ScholarTM

Check

Altmetric


Plumx

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