SurroundNet: Towards Effective Low-Light Image Enhancement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Fei, Sun, Xin, Dong, Junyu, Zhao, Haoran, Zhu, Xiao Xiang
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909815467409408
author Zhou, Fei
Sun, Xin
Dong, Junyu
Zhao, Haoran
Zhu, Xiao Xiang
author_facet Zhou, Fei
Sun, Xin
Dong, Junyu
Zhao, Haoran
Zhu, Xiao Xiang
contents Although Convolution Neural Networks (CNNs) has made substantial progress in the low-light image enhancement task, one critical problem of CNNs is the paradox of model complexity and performance. This paper presents a novel SurroundNet which only involves less than 150$K$ parameters (about 80-98 percent size reduction compared to SOTAs) and achieves very competitive performance. The proposed network comprises several Adaptive Retinex Blocks (ARBlock), which can be viewed as a novel extension of Single Scale Retinex in feature space. The core of our ARBlock is an efficient illumination estimation function called Adaptive Surround Function (ASF). It can be regarded as a general form of surround functions and be implemented by convolution layers. In addition, we also introduce a Low-Exposure Denoiser (LED) to smooth the low-light image before the enhancement. We evaluate the proposed method on the real-world low-light dataset. Experimental results demonstrate that the superiority of our submitted SurroundNet in both performance and network parameters against State-of-the-Art low-light image enhancement methods. Code is available at https: github.com/ouc-ocean-group/SurroundNet.
format Preprint
id arxiv_https___arxiv_org_abs_2110_05098
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle SurroundNet: Towards Effective Low-Light Image Enhancement
Zhou, Fei
Sun, Xin
Dong, Junyu
Zhao, Haoran
Zhu, Xiao Xiang
Computer Vision and Pattern Recognition
Although Convolution Neural Networks (CNNs) has made substantial progress in the low-light image enhancement task, one critical problem of CNNs is the paradox of model complexity and performance. This paper presents a novel SurroundNet which only involves less than 150$K$ parameters (about 80-98 percent size reduction compared to SOTAs) and achieves very competitive performance. The proposed network comprises several Adaptive Retinex Blocks (ARBlock), which can be viewed as a novel extension of Single Scale Retinex in feature space. The core of our ARBlock is an efficient illumination estimation function called Adaptive Surround Function (ASF). It can be regarded as a general form of surround functions and be implemented by convolution layers. In addition, we also introduce a Low-Exposure Denoiser (LED) to smooth the low-light image before the enhancement. We evaluate the proposed method on the real-world low-light dataset. Experimental results demonstrate that the superiority of our submitted SurroundNet in both performance and network parameters against State-of-the-Art low-light image enhancement methods. Code is available at https: github.com/ouc-ocean-group/SurroundNet.
title SurroundNet: Towards Effective Low-Light Image Enhancement
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2110.05098