Low-light image enhancement by deep learning network for improved illumination map

• Published in: Computer vision and image understanding Vol. 232; p. 103681
• Main Authors: Wang, Manli, Li, Jiayue, Zhang, Changsen
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.07.2023
• Subjects: Convolutional neural networks; Depth-separable convolution; Illumination map; Low-light image enhancement; Retinex theory; Depth-separable convolution; Illumination map; 41A10; 65D05; 65D17; Retinex theory; Convolutional neural networks; 41A05; Low-light image enhancement
• ISSN: 1077-3142; 1090-235X
• DOI: 10.1016/j.cviu.2023.103681

In the case of insufficient illumination conditions, the quality of the captured image is poor. At this time, increasing the brightness of the dark region of the whole image will inevitably aggravate noise pollution. Therefore, the ideal state of low-light image enhancement should be to make the dark areas brighter while not allowing the noise part to be enhanced as well. In this paper, we combine Retinex theory and convolutional neural networks to build a simple and effective model with three sub-modules: the decomposition module, illumination module, and reflection module, in which the decomposition module is used to decompose the input low-light image into illumination and reflection maps, the illumination module improves the feature extraction part of the simple convolutional layer used previously and constitutes a new feature extraction structure by Depthwise separable convolution, which makes up for the shortcoming that some dark areas are not well brightened and better adjusts the brightness of the illumination map, and the reflection module adjusts the texture details more clearly because it adds the illumination map as a reference. In this way, the original space is decoupled into two smaller subspaces to the extent that better results can be achieved. We demonstrate through extensive experiments the effectiveness of the design and its superiority over state-of-the-art techniques, especially in terms of robustness to severe visual defects and flexibility in adjusting luminance. •Proposed a low-light image enhancement network with improved illumination.•It enhances image contrast while still maintaining good detail in texture details.•It improves the shortage of KinD+ in dark area brightness enhancement.•Referring to the depth-separable convolution layer used by the lightweight network.•It improves the simple convolution layer used to extract illumination map features.