DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yin, Xiangchen, Yu, Zhenda, Gao, Xin, Sun, Xiao
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913639641907200
author Yin, Xiangchen
Yu, Zhenda
Gao, Xin
Sun, Xiao
author_facet Yin, Xiangchen
Yu, Zhenda
Gao, Xin
Sun, Xiao
contents Low-light image enhancement restores the colors and details of a single image and improves high-level visual tasks. However, restoring the lost details in the dark area is still a challenge relying only on the RGB domain. In this paper, we delve into frequency as a new clue into the model and propose a DCT-driven enhancement transformer (DEFormer) framework. First, we propose a learnable frequency branch (LFB) for frequency enhancement contains DCT processing and curvature-based frequency enhancement (CFE) to represent frequency features. Additionally, we propose a cross domain fusion (CDF) to reduce the differences between the RGB domain and the frequency domain. Our DEFormer has achieved superior results on the LOL and MIT-Adobe FiveK datasets, improving the dark detection performance.
format Preprint
id arxiv_https___arxiv_org_abs_2309_06941
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision
Yin, Xiangchen
Yu, Zhenda
Gao, Xin
Sun, Xiao
Computer Vision and Pattern Recognition
Artificial Intelligence
Low-light image enhancement restores the colors and details of a single image and improves high-level visual tasks. However, restoring the lost details in the dark area is still a challenge relying only on the RGB domain. In this paper, we delve into frequency as a new clue into the model and propose a DCT-driven enhancement transformer (DEFormer) framework. First, we propose a learnable frequency branch (LFB) for frequency enhancement contains DCT processing and curvature-based frequency enhancement (CFE) to represent frequency features. Additionally, we propose a cross domain fusion (CDF) to reduce the differences between the RGB domain and the frequency domain. Our DEFormer has achieved superior results on the LOL and MIT-Adobe FiveK datasets, improving the dark detection performance.
title DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2309.06941