Deep Geometry Post-Processing for Decompressed Point Clouds

• Main Authors: Fan, Xiaoqing, Li, Ge, Li, Dingquan, Ren, Yurui, Gao, Wei, Li, Thomas H
• Format: Journal Article
• Language: English
• Published: 29.04.2022
• Subjects: Computer Science - Computer Vision and Pattern Recognition
• DOI: 10.48550/arxiv.2204.13952

Point cloud compression plays a crucial role in reducing the huge cost of data storage and transmission. However, distortions can be introduced into the decompressed point clouds due to quantization. In this paper, we propose a novel learning-based post-processing method to enhance the decompressed point clouds. Specifically, a voxelized point cloud is first divided into small cubes. Then, a 3D convolutional network is proposed to predict the occupancy probability for each location of a cube. We leverage both local and global contexts by generating multi-scale probabilities. These probabilities are progressively summed to predict the results in a coarse-to-fine manner. Finally, we obtain the geometry-refined point clouds based on the predicted probabilities. Different from previous methods, we deal with decompressed point clouds with huge variety of distortions using a single model. Experimental results show that the proposed method can significantly improve the quality of the decompressed point clouds, achieving 9.30dB BDPSNR gain on three representative datasets on average.