Low-light Image Enhancement with Retinex Decomposition in Latent Space

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zheng, Bolun, Lei, Qingshan, Chen, Quan, Zhang, Qianyu, Yu, Kainan, Jia, Xu, Zhu, Lingyu
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910054595166208
author Zheng, Bolun
Lei, Qingshan
Chen, Quan
Zhang, Qianyu
Yu, Kainan
Jia, Xu
Zhu, Lingyu
author_facet Zheng, Bolun
Lei, Qingshan
Chen, Quan
Zhang, Qianyu
Yu, Kainan
Jia, Xu
Zhu, Lingyu
contents Retinex theory provides a principled foundation for low-light image enhancement, inspiring numerous learning-based methods that integrate its principles. However, existing methods exhibits limitations in accurately decomposing reflectance and illumination components. To address this, we propose a Retinex-Guided Transformer~(RGT) model, which is a two-stage model consisting of decomposition and enhancement phases. First, we propose a latent space decomposition strategy to separate reflectance and illumination components. By incorporating the log transformation and 1-pixel offset, we convert the intrinsically multiplicative relationship into an additive formulation, enhancing decomposition stability and precision. Subsequently, we construct a U-shaped component refiner incorporating the proposed guidance fusion transformer block. The component refiner refines reflectance component to preserve texture details and optimize illumination distribution, effectively transforming low-light inputs to normal-light counterparts. Experimental evaluations across four benchmark datasets validate that our method achieves competitive performance in low-light enhancement and a more stable training process.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15131
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Low-light Image Enhancement with Retinex Decomposition in Latent Space
Zheng, Bolun
Lei, Qingshan
Chen, Quan
Zhang, Qianyu
Yu, Kainan
Jia, Xu
Zhu, Lingyu
Computer Vision and Pattern Recognition
Retinex theory provides a principled foundation for low-light image enhancement, inspiring numerous learning-based methods that integrate its principles. However, existing methods exhibits limitations in accurately decomposing reflectance and illumination components. To address this, we propose a Retinex-Guided Transformer~(RGT) model, which is a two-stage model consisting of decomposition and enhancement phases. First, we propose a latent space decomposition strategy to separate reflectance and illumination components. By incorporating the log transformation and 1-pixel offset, we convert the intrinsically multiplicative relationship into an additive formulation, enhancing decomposition stability and precision. Subsequently, we construct a U-shaped component refiner incorporating the proposed guidance fusion transformer block. The component refiner refines reflectance component to preserve texture details and optimize illumination distribution, effectively transforming low-light inputs to normal-light counterparts. Experimental evaluations across four benchmark datasets validate that our method achieves competitive performance in low-light enhancement and a more stable training process.
title Low-light Image Enhancement with Retinex Decomposition in Latent Space
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.15131