Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lin, Yunlong, Fu, Zhenqi, Wen, Kairun, Ye, Tian, Chen, Sixiang, Meng, Ge, Wang, Yingying, Huang, Yue, Tu, Xiaotong, Ding, Xinghao
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929518491467776
author Lin, Yunlong
Fu, Zhenqi
Wen, Kairun
Ye, Tian
Chen, Sixiang
Meng, Ge
Wang, Yingying
Huang, Yue
Tu, Xiaotong
Ding, Xinghao
author_facet Lin, Yunlong
Fu, Zhenqi
Wen, Kairun
Ye, Tian
Chen, Sixiang
Meng, Ge
Wang, Yingying
Huang, Yue
Tu, Xiaotong
Ding, Xinghao
contents Low-light image enhancement (LIE) aims at precisely and efficiently recovering an image degraded in poor illumination environments. Recent advanced LIE techniques are using deep neural networks, which require lots of low-normal light image pairs, network parameters, and computational resources. As a result, their practicality is limited. In this work, we devise a novel unsupervised LIE framework based on diffusion priors and lookup tables (DPLUT) to achieve efficient low-light image recovery. The proposed approach comprises two critical components: a light adjustment lookup table (LLUT) and a noise suppression lookup table (NLUT). LLUT is optimized with a set of unsupervised losses. It aims at predicting pixel-wise curve parameters for the dynamic range adjustment of a specific image. NLUT is designed to remove the amplified noise after the light brightens. As diffusion models are sensitive to noise, diffusion priors are introduced to achieve high-performance noise suppression. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods in terms of visual quality and efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2409_18899
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors
Lin, Yunlong
Fu, Zhenqi
Wen, Kairun
Ye, Tian
Chen, Sixiang
Meng, Ge
Wang, Yingying
Huang, Yue
Tu, Xiaotong
Ding, Xinghao
Computer Vision and Pattern Recognition
Image and Video Processing
Low-light image enhancement (LIE) aims at precisely and efficiently recovering an image degraded in poor illumination environments. Recent advanced LIE techniques are using deep neural networks, which require lots of low-normal light image pairs, network parameters, and computational resources. As a result, their practicality is limited. In this work, we devise a novel unsupervised LIE framework based on diffusion priors and lookup tables (DPLUT) to achieve efficient low-light image recovery. The proposed approach comprises two critical components: a light adjustment lookup table (LLUT) and a noise suppression lookup table (NLUT). LLUT is optimized with a set of unsupervised losses. It aims at predicting pixel-wise curve parameters for the dynamic range adjustment of a specific image. NLUT is designed to remove the amplified noise after the light brightens. As diffusion models are sensitive to noise, diffusion priors are introduced to achieve high-performance noise suppression. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods in terms of visual quality and efficiency.
title Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2409.18899