Deep Retinex Decomposition for Low-Light Enhancement

14 Aug 2018  ·  Chen Wei, Wenjing Wang, Wenhan Yang, Jiaying Liu ·

Retinex model is an effective tool for low-light image enhancement. It assumes that observed images can be decomposed into the reflectance and illumination. Most existing Retinex-based methods have carefully designed hand-crafted constraints and parameters for this highly ill-posed decomposition, which may be limited by model capacity when applied in various scenes. In this paper, we collect a LOw-Light dataset (LOL) containing low/normal-light image pairs and propose a deep Retinex-Net learned on this dataset, including a Decom-Net for decomposition and an Enhance-Net for illumination adjustment. In the training process for Decom-Net, there is no ground truth of decomposed reflectance and illumination. The network is learned with only key constraints including the consistent reflectance shared by paired low/normal-light images, and the smoothness of illumination. Based on the decomposition, subsequent lightness enhancement is conducted on illumination by an enhancement network called Enhance-Net, and for joint denoising there is a denoising operation on reflectance. The Retinex-Net is end-to-end trainable, so that the learned decomposition is by nature good for lightness adjustment. Extensive experiments demonstrate that our method not only achieves visually pleasing quality for low-light enhancement but also provides a good representation of image decomposition.

PDF Abstract


Introduced in the Paper:


Used in the Paper:


Results from the Paper

Results from Other Papers

Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Low-Light Image Enhancement DICM RetinexNet User Study Score 2.88 # 5
Low-Light Image Enhancement MEF RetinexNet User Study Score 2.80 # 5
Low-Light Image Enhancement VV RetinexNet User Study Score 1.96 # 5


No methods listed for this paper. Add relevant methods here