Efficient cascaded multiscale adaptive network for image restoration

Image restoration, encompassing tasks such as deblurring, denoising, and super-resolution, remains a pivotal area in computer vision. However, efficiently addressing the spatially varying artifacts of various low-quality images with local adaptiveness and handling their degradations at different sca...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHOU, Yichen, ZHOU, Pan, NG, Teck Khim
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2024
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/9641
https://ink.library.smu.edu.sg/context/sis_research/article/10641/viewcontent/Efficient_cascaded_multiscale_adaptive_network_for_image_restoration.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-10641
record_format dspace
spelling sg-smu-ink.sis_research-106412024-12-02T01:45:24Z Efficient cascaded multiscale adaptive network for image restoration ZHOU, Yichen ZHOU, Pan NG, Teck Khim Image restoration, encompassing tasks such as deblurring, denoising, and super-resolution, remains a pivotal area in computer vision. However, efficiently addressing the spatially varying artifacts of various low-quality images with local adaptiveness and handling their degradations at different scales poses significant challenges. To efficiently tackle these issues, we propose the novel Efficient Cascaded Multiscale Adaptive (ECMA) Network. ECMA employs Local Adaptive Module, LAM, which dynamically adjusts convolution kernels across local image regions to efficiently handle varying artifacts. Thus, LAM addresses the local adaptiveness challenge more efficiently than costlier mechanisms like self-attention, due to its less computationally intensive convolutions. To construct a basic ECMA block, three cascading LAMs with convolution kernels from large to small sizes are employed to capture features at different scales. This cascaded multiscale learning effectively handles degradations at different scales, critical for diverse image restoration tasks. Finally, ECMA blocks are stacked in a U-Net architecture to build ECMA networks, which efficiently achieve both local adaptiveness and multiscale processing. Experiments show ECMA’s high performance and efficiency, achieving comparable or superior restoration performance to state-of-the-art methods while reducing computational costs by 1.2× to 9.7× across various image restoration tasks, e.g., image deblurring, denoising and super-resolution. 2024-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9641 https://ink.library.smu.edu.sg/context/sis_research/article/10641/viewcontent/Efficient_cascaded_multiscale_adaptive_network_for_image_restoration.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Image deblurring Image denoising Image super-resolution Image restoration Artificial Intelligence and Robotics Numerical Analysis and Scientific Computing
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Image deblurring
Image denoising
Image super-resolution
Image restoration
Artificial Intelligence and Robotics
Numerical Analysis and Scientific Computing
spellingShingle Image deblurring
Image denoising
Image super-resolution
Image restoration
Artificial Intelligence and Robotics
Numerical Analysis and Scientific Computing
ZHOU, Yichen
ZHOU, Pan
NG, Teck Khim
Efficient cascaded multiscale adaptive network for image restoration
description Image restoration, encompassing tasks such as deblurring, denoising, and super-resolution, remains a pivotal area in computer vision. However, efficiently addressing the spatially varying artifacts of various low-quality images with local adaptiveness and handling their degradations at different scales poses significant challenges. To efficiently tackle these issues, we propose the novel Efficient Cascaded Multiscale Adaptive (ECMA) Network. ECMA employs Local Adaptive Module, LAM, which dynamically adjusts convolution kernels across local image regions to efficiently handle varying artifacts. Thus, LAM addresses the local adaptiveness challenge more efficiently than costlier mechanisms like self-attention, due to its less computationally intensive convolutions. To construct a basic ECMA block, three cascading LAMs with convolution kernels from large to small sizes are employed to capture features at different scales. This cascaded multiscale learning effectively handles degradations at different scales, critical for diverse image restoration tasks. Finally, ECMA blocks are stacked in a U-Net architecture to build ECMA networks, which efficiently achieve both local adaptiveness and multiscale processing. Experiments show ECMA’s high performance and efficiency, achieving comparable or superior restoration performance to state-of-the-art methods while reducing computational costs by 1.2× to 9.7× across various image restoration tasks, e.g., image deblurring, denoising and super-resolution.
format text
author ZHOU, Yichen
ZHOU, Pan
NG, Teck Khim
author_facet ZHOU, Yichen
ZHOU, Pan
NG, Teck Khim
author_sort ZHOU, Yichen
title Efficient cascaded multiscale adaptive network for image restoration
title_short Efficient cascaded multiscale adaptive network for image restoration
title_full Efficient cascaded multiscale adaptive network for image restoration
title_fullStr Efficient cascaded multiscale adaptive network for image restoration
title_full_unstemmed Efficient cascaded multiscale adaptive network for image restoration
title_sort efficient cascaded multiscale adaptive network for image restoration
publisher Institutional Knowledge at Singapore Management University
publishDate 2024
url https://ink.library.smu.edu.sg/sis_research/9641
https://ink.library.smu.edu.sg/context/sis_research/article/10641/viewcontent/Efficient_cascaded_multiscale_adaptive_network_for_image_restoration.pdf
_version_ 1819113090071920640