LIELFormer: Low-Light Image Enhancement with a Lightweight Transformer

Images captured under low-light conditions often suffer from (partially) poor visibility. One of the challenges of low-light enhancement, in addition to inadequate lighting, is noise and color distortion due to the limited quality of the cameras. Previous researchers have typically used paired data (low-light and high-definition images) for training to solve single-image enhancement problems. However, those approaches have two disadvantages. One is the difficulty of collecting data in pairs, which wastes time and computational resources. Secondly, such models tend to be poorly generalizable and perform poorly on multiple datasets. Due to the consistent distribution of noise and low light intensity in specific datasets, models often perform poorly when faced with more adverse conditions. This paper proposes a simple but accurate single image enhancement network to solve this problem. Our network consists of the light estimation module and the color correction module. The light estimation module is based on the Retinex principle and uses CNN to enhance illumination. The color correction module uses a global prediction module (transformer block) to obtain the actual color distribution. This module extracts the image’s original colors to make it more realistic. Our network structure is simple and does not require any paired or unpaired data for auxiliary training. It allows a single image enhancement task to be performed using only iterations of the image itself. Our approach outperforms current state-of-the-art methods in qualitative and quantitative experiments. We will release our code after publication.