Deep Learning-Based Point Cloud Geometry Coding: RD Control Through Implicit and Explicit Quantization

Abstract

Deep learning is becoming more and more relevant for multiple multimedia processing tasks, and lately it has raised much interest in the coding arena notably for images and point clouds. While offering near state-of-the-art compression performance, current deep learning-based point cloud coding solutions have a shortcoming since they require training and storing multiple models in order to obtain different rate-distortion trade-offs. This paper proposes a solution that effectively reduces the number of deep learning models that need to be trained and stored by applying explicit quantization to the latent representation, which can be controlled at coding time, to generate varying rate-distortion tradeoffs. The proposed implicit-explicit quantization combination achieves a compression performance that is equivalent or better than the alternative, while significantly reducing the model storage memory requirements.