Learning end-to-end depth maps compression with conditional quality-controllable autoencoder

3D video is leading to the emergence of new technologies, such as virtual, augmented, and mixed realities, which find applications in several fields mainly healthcare, education, and industry. Even for the Internet of Things (IoT), the future lies in 3D vision and depth for machines such as autonomous cars, robots, and drones to have a deep perception like humans. Texture-dedicated compression methods are not efficient for depth maps due to features distinctions between depth and texture images. To tackle this issue, we propose a learning variable-rate depth map compression model with conditional quality-controllable autoencoder. Specifically, the encoder extracts deep features from depth maps through an advanced Convolutional Neural Network (CNN) model, trained using a combination of grayscale texture and depth images. This latter incorporates an initial layer of predefined wedgelet filters, succeeded by a VGG 19 pretrained model. To effectively differentiate between depth maps and grayscale textures within the training dataset, an image style classification technique using the learnt deep correlation Features is employed. Our end-to-end compression network ensures better performances over main candidate methods and depth-oriented 3D-HEVC compression standard.