<p>Image acquired by camera sensors suffers from low contrast and poor visibility under low-light conditions. We observe that low-light images exhibit a lower signal-to-noise ratio, resulting in a mixture of fine details, textures, and noise, making it challenging to reconstruct small-scale textures in the image. Inspired by this observation, we propose a SNR-guided CNN-Transformer network for high frequency restoration during low light image enhancement. We propose a multi scale contrastive aware attention module for low and high frequency image decomposition. The attention module leverages different scale receptive fields of convolutional layers, which extract both high frequency and low frequency features images. The low-frequency image is processed by a trainable Low Frequency SNR Perception module, resulting in excellent denoising performance and generating SNR-enhanced images with clearer edge contours. Then, the Low Frequency SNR guided self attention mechanism is proposed for high frequency image restoration. The SNR attention selects the detail regions from the high frequency components corresponding to the structure regions (i.e., the high SNR values) in the low frequency components. And the fine details are restored in these regions using transformer module. The subjective and objective experiments demonstrate that our proposed method outperforms existing approaches in terms of detail and structure preservation.</p>