PCHM-Net: A New Point Cloud Compression Framework for Both Human Vision and Machine Vision
Lei Liu, Zhihao Hu, Jing Zhang
Abstract
Recently, point cloud data has attracted increasing attention in various machine vision tasks like classification and detection. However, directly transmitting the raw point cloud for such machine vision tasks will bring a huge bit-rate cost. In this work, we propose a new point cloud compression framework called PCHM-Net for both human vision and machine vision. Our proposed PCHM-Net adopts a two-branch structure with the shared octree-based compression module. To better compress the point cloud data and save bit-rate for machine vision tasks, we use the point cloud selection module to select a sparse set of points before octree construction, which allows us to use deeper octree structure and thus better reconstruct the point cloud coordinates for more discriminative feature extraction. We further propose a global feature aggregation-based classification module to deal with the sparse point cloud classification task. Comprehensive experiments on various point cloud benchmark datasets (e.g., ModelNet, ShapeNet and ScanNet) demonstrate that our newly proposed PCHM-Net achieves promising coding performance for both human vision and machine vision.