Troublemaker Learning for Low-Light Image Enhancement

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Song, Yinghao, Cao, Zhiyuan, Xiang, Wanhong, Long, Sifan, Yang, Bo, Ge, Hongwei, Liang, Yanchun, Wu, Chunguo
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913251394060288
author Song, Yinghao
Cao, Zhiyuan
Xiang, Wanhong
Long, Sifan
Yang, Bo
Ge, Hongwei
Liang, Yanchun
Wu, Chunguo
author_facet Song, Yinghao
Cao, Zhiyuan
Xiang, Wanhong
Long, Sifan
Yang, Bo
Ge, Hongwei
Liang, Yanchun
Wu, Chunguo
contents Low-light image enhancement (LLIE) restores the color and brightness of underexposed images. Supervised methods suffer from high costs in collecting low/normal-light image pairs. Unsupervised methods invest substantial effort in crafting complex loss functions. We address these two challenges through the proposed TroubleMaker Learning (TML) strategy, which employs normal-light images as inputs for training. TML is simple: we first dim the input and then increase its brightness. TML is based on two core components. First, the troublemaker model (TM) constructs pseudo low-light images from normal images to relieve the cost of pairwise data. Second, the predicting model (PM) enhances the brightness of pseudo low-light images. Additionally, we incorporate an enhancing model (EM) to further improve the visual performance of PM outputs. Moreover, in LLIE tasks, characterizing global element correlations is important because more information on the same object can be captured. CNN cannot achieve this well, and self-attention has high time complexity. Accordingly, we propose Global Dynamic Convolution (GDC) with O(n) time complexity, which essentially imitates the partial calculation process of self-attention to formulate elementwise correlations. Based on the GDC module, we build the UGDC model. Extensive quantitative and qualitative experiments demonstrate that UGDC trained with TML can achieve competitive performance against state-of-the-art approaches on public datasets. The code is available at https://github.com/Rainbowman0/TML_LLIE.
format Preprint
id arxiv_https___arxiv_org_abs_2402_04584
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Troublemaker Learning for Low-Light Image Enhancement
Song, Yinghao
Cao, Zhiyuan
Xiang, Wanhong
Long, Sifan
Yang, Bo
Ge, Hongwei
Liang, Yanchun
Wu, Chunguo
Image and Video Processing
Computer Vision and Pattern Recognition
Low-light image enhancement (LLIE) restores the color and brightness of underexposed images. Supervised methods suffer from high costs in collecting low/normal-light image pairs. Unsupervised methods invest substantial effort in crafting complex loss functions. We address these two challenges through the proposed TroubleMaker Learning (TML) strategy, which employs normal-light images as inputs for training. TML is simple: we first dim the input and then increase its brightness. TML is based on two core components. First, the troublemaker model (TM) constructs pseudo low-light images from normal images to relieve the cost of pairwise data. Second, the predicting model (PM) enhances the brightness of pseudo low-light images. Additionally, we incorporate an enhancing model (EM) to further improve the visual performance of PM outputs. Moreover, in LLIE tasks, characterizing global element correlations is important because more information on the same object can be captured. CNN cannot achieve this well, and self-attention has high time complexity. Accordingly, we propose Global Dynamic Convolution (GDC) with O(n) time complexity, which essentially imitates the partial calculation process of self-attention to formulate elementwise correlations. Based on the GDC module, we build the UGDC model. Extensive quantitative and qualitative experiments demonstrate that UGDC trained with TML can achieve competitive performance against state-of-the-art approaches on public datasets. The code is available at https://github.com/Rainbowman0/TML_LLIE.
title Troublemaker Learning for Low-Light Image Enhancement
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.04584