To address the challenges of collecting paired datasets in coal mine underground environments and the issues of low brightness in collected images that hinder subsequent recognition tasks, an improved CycleGAN-based low-light image enhancement method is proposed. To solve the difficulty of paired dataset collection, CycleGAN is chosen for unsupervised learning. To enhance the feature extraction capability of the generator, the Efficient Channel Attention (ECA) is introduced. A dilated residual convolutional brightness enhancement module is added to the generator to improve the brightness of underground images. Finally, to avoid over-enhancement and distortion, InstanceNorm (IN) in CycleGAN is replaced with Adaptive Layer-Instance Normalization (AdaLIN). Experimental results show that the proposed method has averaged an improvement of 9.00% in PSNR, 5.55% in SSIM, 1.70% in EN, and 7.61% in VIF compared to the conventional CycleGAN method, effectively enhancing the brightness and clarity of contours in coal mine underground images.