Illumination Distribution Prior for Low-light Image Enhancement

Chao Wang, Yang Zhou, Liangtian He, Lin Fenglai, Hongming Chen, Liang-Jian Deng

Abstract: In this paper, we propose a simple but effective illumination distribution prior (IDP) for images to illuminate the darkness. The illumination distribution prior is the product of a statistical approach to low-light images. It is based on a key factor - the mean value and standard deviation of images are positively correlated with the illumination. Using IDP in combination with the dual-domain feature fusion network (DFFN), we can obtain images that are more consistent with the ground truth distribution. DFFN inserts the discrete wavelet transform (DWT) into the transformer architecture, aiming to recover the detailed texture of the image through local high-frequency information and global spatial information. We have conducted extensive experiments on five widely used low-light image enhancement datasets and the experimental results show the superior performance of our proposed network (IDP-Net) compared to other state-of-the-art methods.

Primary Subject Area: [Content] Vision and Language

Secondary Subject Area: [Content] Multimodal Fusion

Relevance To Conference: Low-light image enhancement has always been a core issue in multimedia visual processing. It can effectively enhance the image quality under adverse conditions, laying the foundation for specific applications in the multimedia field. With the support of high-quality images/videos, multimedia tasks can be completed effectively. Therefore, we believe that the research content of this paper is suitable for the domain scope of MM24.

Submission Number: 2690