Llrnet: A Multiscale Subband Learning Approach for Low Light Image Restoration

We consider the problem of low light image restoration through joint contrast enhancement and denoising. Deep convolutional neural networks (CNNs) based on residual learning have been successful in achieving state of the art performance in image denoising. However, their application to joint contrast enhancement and denoising poses challenges owing to the nature of the distortion process involving both loss of details and noise. Thus, we propose a multiscale learning approach by learning the subbands obtained in a Laplacian pyramid decomposition through a subband CNN (SCNN). The enhanced subbands at multiple scales are then combined to obtain the final restored image using a recomposition CNN (ReCNN). We refer to the overall network involving SCNN and ReCNN as low light restoration network (LLRNet). We show through extensive experiments based on the `See in the Dark' Dataset that our approach produces better quality restored images when compared to other contrast enhancement techniques and CNN based approaches.