UMLE: Unsupervised Multi-discriminator Network for Low Light Enhancement
This work is significant for improving the reliability of vision-based applications in automated driving by enhancing images captured in low-light conditions.
This paper addresses the challenge of low-light image enhancement, crucial for applications like automated driving, by proposing an unsupervised generative adversarial network (GAN) with multiple discriminators. The method achieves superior qualitative and quantitative results compared to state-of-the-art methods, leading to significant improvements in autopilot positioning and detection.
Low-light image enhancement, such as recovering color and texture details from low-light images, is a complex and vital task. For automated driving, low-light scenarios will have serious implications for vision-based applications. To address this problem, we propose a real-time unsupervised generative adversarial network (GAN) containing multiple discriminators, i.e. a multi-scale discriminator, a texture discriminator, and a color discriminator. These distinct discriminators allow the evaluation of images from different perspectives. Further, considering that different channel features contain different information and the illumination is uneven in the image, we propose a feature fusion attention module. This module combines channel attention with pixel attention mechanisms to extract image features. Additionally, to reduce training time, we adopt a shared encoder for the generator and the discriminator. This makes the structure of the model more compact and the training more stable. Experiments indicate that our method is superior to the state-of-the-art methods in qualitative and quantitative evaluations, and significant improvements are achieved for both autopilot positioning and detection results.