Low-light Image Enhancement with Retinex Decomposition in Latent Space

Bolun Zheng; Qingshan Lei; Quan Chen; Qianyu Zhang; Kainan Yu; Xu Jia; Lingyu Zhu

cs.CVMar 16, 2026

Low-light Image Enhancement with Retinex Decomposition in Latent Space

Authors: Bolun Zheng, Qingshan Lei, Quan Chen, Qianyu Zhang, Kainan Yu, Xu Jia, Lingyu Zhu

Organizations: School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China · College of Artificial Intelligence, Jiaxing University, Jiaxing 314001, China · School of Artificial Intelligence at Dalian University of Technology, Dalian 116000, China · Department of Computer Science at City University of Hong Kong, Hong Kong, China

Abstract

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.

Figures & tables

Fig. 1: Comparison between the typical Retinex decomposition strategy and our method in deep learning frameworks.

Fig. 2: The overview of the RGT model. (a) Decomposition takes a paired low-light/normal-light image as input during training to decompose the image into $R$ and $L$ components. (b) RGT extracts $R$ and $L$ using the pre-trained decomposition network (frozen parameters) and enhances $R$ and $L$ separately via the Enhancer network (non-shared parameters). Then, reconstructing the final enhanced result by combining processed $R$ and $L$ .

Fig. 4: Schematic illustration of illumination-reflectance component swapping between two content-identical images under different lighting conditions. Each input image is decomposed into reflectance ( $R$ ) and illumination ( $L$ ) components within the shallow spatial space. By exclusively exchanging the $L$ components between paired images, we can synthesize four novel recomposed results. Ideally, swapping only the $L$ components is sufficient to alter the brightness of the images.

Methods	LOLv2_real				LOLv2_syn
Methods	$f_{rec}(R_{l},L_{l})$	$f_{rec}(R_{l},L_{n})$	$f_{rec}(R_{n},L_{l})$	$f_{rec}(R_{n},L_{n})$	$f_{rec}(R_{l},L_{l})$	$f_{rec}(R_{l},L_{n})$	$f_{rec}(R_{n},L_{l})$	$f_{rec}(R_{n},L_{n})$
RetinexNet [ 4 ]	38.56	23.90	35.47	29.50	36.44	20.37	26.59	30.28
RetinexDIP [ 58 ]	16.61	14.91	14.49	18.05	23.75	14.43	23.52	20.47
URetinexNet [ 59 ]	34.85	19.40	31.47	24.76	26.78	17.39	25.36	22.89
RGT	69.45	54.77	68.34	59.05	58.22	51.11	56.82	53.72

TABLE I: The PSNR of comparative decomposition on LOLv2 dataset.

f_{rec}

represents the operation of reconstructing the image from

R

and

L

components. According to RetinexNet [ 4 ] requirements for the decomposed

R

and

L

components, the reconstructed images from

R

and

L

should match the input image corresponding to

L

Fig. 5: Visual comparisons of the decomposed results by different methods on LOLv2_real. The images within the green boxes should be same and the images within the red boxes should be same.

Methods	LOLv2_real		LOLv2_syn		HDR+(480p)		SDSD-indoor		SICE		Complexity
Methods	PSNR	SSIM	PSNR	SSIM	PSNR	SSIM	PSNR	SSIM	PSNR	SSIM	FLOPs(G)	Params(M)	Time(ms)
RetinexNet [ 4 ]	16.52	0.674	19.11	0.805	19.54	0.678	25.88	0.832	19.71	0.686	587.47	0.84	3.36
LLFlow [ 70 ]	20.41	0.829	23.14	0.930	22.96	0.762	22.10	0.801	19.99	0.685	358.40	17.42	122.70
MirNetv2 [ 71 ]	22.00	0.818	24.86	0.925	22.87	0.765	29.68	0.870	24.29	0.767	140.21	5.86	61.69
SNR-Net [ 72 ]	21.48	0.849	24.14	0.928	22.50	0.764	29.44	0.894	21.78	0.729	26.35	4.01	6.25
GSAD [ 73 ]	22.20	0.811	22.46	0.897	18.03	0.781	–	–	15.11	0.553	134.04	18.42	164.99

TABLE II: Quantitative comparisons PSNR/SSIM on LOLv2 [ 5 ] , HDR+ [ 6 ] , SDSD(indoor) [ 7 ] and SICE [ 8 ] datasets. The highest result is in bold while the second highest result is underlined .

Fig. 6: Visual comparisons of the enhanced results by different methods on LOLv2_real (top) and LOLv2_syn (bottom).

Fig. 7: Visual comparisons of the enhanced results by different methods on HDR+(480p) (top), SICE (middle) and SDSD-indoor (bottom)

Methods	LOLv2_real	LOLv2_syn	HDR+(480p)	SDSD-indoor	SICE
SNR-Net [ 72 ]	0.122	0.061	0.238	0.230	0.206
CSPN [ 75 ]	0.156	0.055	0.071	0.181	0.235
IGDFormer [ 77 ]	0.158	0.074	0.086	0.227	0.237
AttnFlow [ 76 ]	0.146	0.050	0.064	0.223	0.298
RetinexMamba [ 78 ]	0.147	0.062	0.073	0.184	0.230
CIDNet [ 79 ]	0.131	0.055	0.086	0.198	0.258

TABLE III: Quantitative comparisons LPIPS

\downarrow

on LOLv2 [ 5 ] , HDR+(480p) [ 6 ] , SDSD(indoor) [ 7 ] and SICE [ 8 ] datasets. The highest result is in bold while the second highest result is underlined .

Methods	DICM		LIME		MEF		NPE		VV
Methods	CLIP-IQA $\uparrow$	NIQE $\downarrow$	CLIP-IQA $\uparrow$	NIQE $\downarrow$	CLIP-IQA $\uparrow$	NIQE $\downarrow$	CLIP-IQA $\uparrow$	NIQE $\downarrow$	CLIP-IQA $\uparrow$	NIQE $\downarrow$
SNR-Net [ 72 ]	0.599	4.71	0.665	5.74	0.633	4.18	0.544	4.32	0.304	9.87
CSPN [ 75 ]	0.659	4.10	0.626	4.12	0.604	4.42	0.668	3.97	0.297	3.24
IGDFormer [ 77 ]	0.652	3.77	0.665	3.96	0.688	3.51	0.530	4.30	0.313	2.99
AttnFlow [ 76 ]	0.730	4.54	0.712	4.46	0.746	4.64	0.683	4.24	0.352	3.00
RetinexMamba [ 78 ]	0.665	3.79	0.691	3.96	0.673	3.35	0.573	3.92	0.384	2.90

TABLE IV: Quantitative comparisons CLIP-IQA

\uparrow

/NIQE

\downarrow

on DICM [ 60 ] , LIME [ 61 ] , MEF [ 62 ] , NPE [ 63 ] and VV [ 64 ] datasets. The highest result is in bold while the second highest result is underlined .

Fig. 8: Visual comparisons of the enhanced results by different methods on unpaired dataset (DICM, LIME, MEF, NPE and VV).

Fig. 9: Visual comparison of various methods on real-world images from various mobile devices.

Methods	$f_{rec}(R_{l},L_{l})$	$f_{rec}(R_{l},L_{n})$	$f_{rec}(R_{n},L_{l})$	$f_{rec}(R_{n},L_{n})$	PSNR	SSIM
(0)	40.35	30.84	39.91	38.35	21.76	0.844
(1)	50.16	23.56	42.76	38.52	22.30	0.844
(2)	52.73	48.19	51.77	51.58	23.27	0.811
(3)	51.12	22.83	39.03	50.53	22.63	0.832
Ours	69.45	54.77	68.34	59.05	23.80	0.896

TABLE V: Ablation study on decomposition strategies using the LOLv2_real benchmark. Subscripts

l/n

denote components derived from low-light and normal images respectively.

Fig. 10: The overview of four variant decomposition strategies.

Inputs	Methods	$f_{rec}(R_{l},L_{l})$	$f_{rec}(R_{l},L_{n})$	$f_{rec}(R_{n},L_{l})$	$f_{rec}(R_{n},L_{n})$	Avg
Low $\leftrightarrow$ Middle	(1)	57.27	46.19	46.18	57.33	51.74
	(2)	64.74	59.52	62.16	61.03	61.86
	Ours	68.00	61.92	66.86	62.73	64.88
Middle $\leftrightarrow$ High	(1)	58.38	41.27	39.42	50.39	47.37
	(2)	61.03	57.39	58.29	59.18	58.97
	Ours	62.73	57.62	61.38	58.78	60.13

TABLE VI: Ablation study on decomposition strategies using the Kalantri dataset. Based on the types of input image pairs, the experiments can be divided into three groups:(i) Low

\leftrightarrow

Middle; (ii) Middle

\leftrightarrow

High; (iii) Low

\leftrightarrow

High. Each group employs three decomposition strategies for the experiments, including the classical Retinex strategy (variant (1)), variant (2), and the full strategy (Ours).

Methods	$f_{rec}(R_{l},L_{l})$	$f_{rec}(R_{l},L_{n})$	$f_{rec}(R_{n},L_{l})$	$f_{rec}(R_{n},L_{n})$	Avg
RetinexNet	38.56	23.90	35.47	29.50	31.86
RetinexNet*	58.27	45.09	57.84	50.23	52.86
URetinexNet	34.85	19.40	31.47	24.76	27.62
URetinexNet*	56.75	45.35	56.35	47.13	51.40
Ours	69.45	54.77	68.34	59.05	62.91

TABLE VII: Ablation study on decomposition strategies using the LOLv2_real benchmark. Subscripts

l/n

denote components derived from low-light and normal images respectively. * denotes the model employs the latent space decomposition strategy.

Fig. 11: Comparison of training stability between additive and multiplicative decompositions. Each model is trained 10 times, and the figure shows the mean and variance of the loss at each epoch.

Fig. 12: The overview of three GFTB variants and complete GFTB.

Different GFTB structures								Metrics
Variants				R		L		Metrics
(a) SA	(b) $\odot V$	(c) $\odot f_{in}$	(d) CA	$S_{mean}$	$S_{max}$	$S_{mean}$	$S_{max}$	PSNR	SSIM
✓								22.99	0.837
	✓			✓			✓	23.03	0.792
		✓		✓			✓	21.85	0.815
			✓	✓		✓		23.53	0.855

TABLE VIII: Ablation study on different GFTB structures.

Explore similar work

WREN: Low Light Image Enhancement Using Retinex theory-based Double U-Net-like Structures
Jul 17, 2026Reina Kaneko, Junya Hara, Hiroshi Higashi +1Image Enhancement U-Net
The University of Osaka, Osaka, Japan · Kansai University, Osaka, Japan
InterLight: Leveraging Intrinsic Illumination Priors for Low-Light Image Enhancement
May 19, 2026Ziqi Wang, Xu Zhang, Laibin Chang +3Image Enhancement Low-Light Image Enhancement
National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University · Department of Computer Science, University of Macau · Department of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence +1
M2Retinexformer: Multi-Modal Retinexformer for Low-Light Image Enhancement
May 11, 2026Youssef Aboelwafa, Hicham G. Elmongui, Marwan TorkiImage Enhancement Low-Light Image Enhancement
Alexandria University, Egypt

Jul 17, 2026J/K move · Enter open · S save

WREN: Low Light Image Enhancement Using Retinex theory-based Double U-Net-like Structures

Reina Kaneko, Junya Hara, Hiroshi Higashi, Yuichi Tanaka

The University of Osaka, Osaka, Japan · Kansai University, Osaka, Japan

Image Enhancement U-Net Low-Light Image Enhancement

Open paper AskPDF arXiv

This paper proposes a neural network for low light image enhancement (LLIE) based on retinex theory to make LLIE robust for various dynamic range scenes. The retinex theory is an image formulation model inspired by a human color perception hypothesis, where a low light image is decomposed into intrinsic color context (i.e., reflectance map) and scene-dependent illumination (i.e., illumination map). Due to non-uniqueness of its decomposition, existing retinex-based LLIE methods often fail to achieve stable decomposition, which lead to over-enhancement. Typically, they are sensitive to the dynamic ranges that vary in different lighting conditions. To tackle this issue, we propose WREN: An LLIE neural network with double U-Net-like structures. WREN consists of two U-Net-like sub-networks. The first network has one encoder and two decoders that decompose an input image into the reflectance and illumination maps. The second network with a customized Transformer block between an encoder and a decoder only enhances the illumination map obtained from the first network: This completely follows the assumption of the retinex theory. Finally, the enhanced illumination map is recombined with the reflectance map. The network is trained end-to-end with a scale-invariant loss function, which gives robustness against the illumination scaling. Numerical results show that our method achieves the state-of-the-art performance across multiple datasets. Our code is available online.

Abstract

Explore similar work

WREN: Low Light Image Enhancement Using Retinex theory-based Double U-Net-like Structures

InterLight: Leveraging Intrinsic Illumination Priors for Low-Light Image Enhancement

M2Retinexformer: Multi-Modal Retinexformer for Low-Light Image Enhancement