Towards image denoising in the latent space of learning-based compression

In recent years, learning-based image compression has demonstrated similar or superior performance when com- pared to conventional approaches in terms of compression efficiency and visual quality. Typically, learning-based image compression takes advantage of autoencoders, which are architectures consisting of two main parts: a multi-layer neural network encoder and its dual decoder. The encoder maps the input image represented in the pixel domain to a compact representation, also known as latent space. Consequently, the decoder reconstructs the original image in the pixel domain from its latent representation, as accurately as possible. Traditionally, image processing algorithms, and in particular image denoising, are applied to images in the pixel domain before compression, and eventually in some cases as a post-processing stage after decompression. In this context, the combination of denoising operations with the autoencoder might reduce the computational cost while achieving similar performance in accuracy. In this paper, the idea of combining the image denoising task with compression is examined. In particular, the integration of denoising convolutional layers in the decoder of a learning-based compression network is investigated. Results show that, while the rate-distortion performance of the method is slightly reduced, a gain in the computational complexity can be achieved.