Abstract: In the process of digitizing and transmitting information, due to the limitations of imaging equipment and the interference of external environment, remote sensing images often contain a lot of noise, which leads to the degradation of image quality and adversely affects subsequent image processing. In this paper, a remote sensing image denoising algorithm based on convolutional neural network is proposed. The algorithm considers the image denoising process as the neural network fitting process. Using the residual learning strategy and the deep neural network with batch regularization layer, it can denoise the remote sensing images with various noise levels. Experiments show that the proposed algorithm not only effectively improves the denoising effect, but also shortens the training time of the network.