Learning point and contextual processing networks for low-light image enhancement

Point processing techniques, such as the gamma correction, are classical methods for low-light image enhancement. These methods are efficient, explicit, and interpretable. However, to tackle images of various light conditions, these methods need to be set meticulously and accordingly. To tackle this...

Full description

Saved in:
Bibliographic Details
Main Author: Zheng, Bowen
Other Authors: Jiang Xudong
Format: Thesis-Master by Research
Language:English
Published: Nanyang Technological University 2021
Subjects:
Online Access:https://hdl.handle.net/10356/152819
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-152819
record_format dspace
spelling sg-ntu-dr.10356-1528192023-07-04T17:40:00Z Learning point and contextual processing networks for low-light image enhancement Zheng, Bowen Jiang Xudong School of Electrical and Electronic Engineering EXDJiang@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Engineering::Electrical and electronic engineering Point processing techniques, such as the gamma correction, are classical methods for low-light image enhancement. These methods are efficient, explicit, and interpretable. However, to tackle images of various light conditions, these methods need to be set meticulously and accordingly. To tackle this issue, I propose to combine these traditional methods with the powerful learning ability of convolutional neural networks (CNNs). Specifically, I propose a point and contextual processing network (PCPNet) consisting of two parallel branches: In the point processing branch, given an input image, a set of hidden intensities images (HIIs) are predicted, as well as a set of parameters governing the gamma corrections performing on the HIIs. Due to the nonlinearity of the gamma corrections, we can obtain diverse and complex enhancement effects merely with a shallow network (of 3 layers). This further guarantees the efficiency of the point processing branch, and allows the HIIs to be generated with the full resolution and preserve the details. While in the contextual processing branch, an encoder-decoder structure is adopted to explore contextual information, which helps to alleviate the effects of noise. The outputs of these two branches are combined as the final enhancement result. Extensive experiments on multiple datasets, including LOL, MIT, and ExDark, validate the effectiveness of the proposed method. Master of Engineering 2021-10-05T04:22:45Z 2021-10-05T04:22:45Z 2021 Thesis-Master by Research Zheng, B. (2021). Learning point and contextual processing networks for low-light image enhancement. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/152819 https://hdl.handle.net/10356/152819 10.32657/10356/152819 en This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0). application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Engineering::Electrical and electronic engineering
spellingShingle Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Engineering::Electrical and electronic engineering
Zheng, Bowen
Learning point and contextual processing networks for low-light image enhancement
description Point processing techniques, such as the gamma correction, are classical methods for low-light image enhancement. These methods are efficient, explicit, and interpretable. However, to tackle images of various light conditions, these methods need to be set meticulously and accordingly. To tackle this issue, I propose to combine these traditional methods with the powerful learning ability of convolutional neural networks (CNNs). Specifically, I propose a point and contextual processing network (PCPNet) consisting of two parallel branches: In the point processing branch, given an input image, a set of hidden intensities images (HIIs) are predicted, as well as a set of parameters governing the gamma corrections performing on the HIIs. Due to the nonlinearity of the gamma corrections, we can obtain diverse and complex enhancement effects merely with a shallow network (of 3 layers). This further guarantees the efficiency of the point processing branch, and allows the HIIs to be generated with the full resolution and preserve the details. While in the contextual processing branch, an encoder-decoder structure is adopted to explore contextual information, which helps to alleviate the effects of noise. The outputs of these two branches are combined as the final enhancement result. Extensive experiments on multiple datasets, including LOL, MIT, and ExDark, validate the effectiveness of the proposed method.
author2 Jiang Xudong
author_facet Jiang Xudong
Zheng, Bowen
format Thesis-Master by Research
author Zheng, Bowen
author_sort Zheng, Bowen
title Learning point and contextual processing networks for low-light image enhancement
title_short Learning point and contextual processing networks for low-light image enhancement
title_full Learning point and contextual processing networks for low-light image enhancement
title_fullStr Learning point and contextual processing networks for low-light image enhancement
title_full_unstemmed Learning point and contextual processing networks for low-light image enhancement
title_sort learning point and contextual processing networks for low-light image enhancement
publisher Nanyang Technological University
publishDate 2021
url https://hdl.handle.net/10356/152819
_version_ 1772828491601936384