Point Cloud Attribute Compression Via Clustering And Intra Prediction

With the rapid development of 3D capture technologies, point cloud has been widely used in many emerging applications such as augmented reality, autonomous driving, and 3D printing. However, point cloud, used to represent real world objects in these applications, may contain millions of points, which results in huge data volume. Therefore, efficient compression algorithms are essential for point cloud when it comes to storage and real-time transmission issues. Specially, the attribute compression of point cloud is still challenging owing to the sparsity and irregular distribution of corresponding points in 3D space. In this paper, we present a novel point cloud attribute compression scheme based on hierarchical clustering and 3D intra prediction. Unlike the commonly used octree decomposition based compression approaches, we divide point cloud into distinguishing clusters by a hierarchical clustering algorithm. Accordingly, a genetic algorithm based intra prediction is introduced to organize the irregularly distributed points in each cluster, and the color attributes of these points are mapped to 2D uniform grids. Finally, a well-developed image coding method is leveraged to achieve adorable compression performance. Experimental results demonstrate that the proposed scheme is much more efficient than traditional attribute compression schemes.