Affiliation:
1. School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China
Abstract
Due to the often substantial size of the real-world point cloud data, efficient transmission and storage have become critical concerns. Point cloud compression plays a decisive role in addressing these challenges. Recognizing the importance of capturing global information within point cloud data for effective compression, many existing point cloud compression methods overlook this crucial aspect. To tackle this oversight, we propose an innovative end-to-end point cloud compression method designed to extract both global and local information. Our method includes a novel Transformer module to extract rich features from the point cloud. Utilization of a pooling operation that requires no learnable parameters as a token mixer for computing long-distance dependencies ensures global feature extraction while significantly reducing both computations and parameters. Furthermore, we employ convolutional layers for feature extraction. These layers not only preserve the spatial structure of the point cloud, but also offer the advantage of parameter independence from the input point cloud size, resulting in a substantial reduction in parameters. Our experimental results demonstrate the effectiveness of the proposed TransPCGC network. It achieves average Bjontegaard Delta Rate (BD-Rate) gains of 85.79% and 80.24% compared to Geometry-based Point Cloud Compression (G-PCC). Additionally, in comparison to the Learned-PCGC network, our approach attains an average BD-Rate gain of 18.26% and 13.83%. Moreover, it is accompanied by a 16% reduction in encoding and decoding time, along with a 50% reduction in model size.
Funder
National Key R&D Program of China
Subject
Computational Mathematics,Computational Theory and Mathematics,Numerical Analysis,Theoretical Computer Science
Reference65 articles.
1. Zhu, Z., Peng, S., Larsson, V., Xu, W., Bao, H., Cui, Z., Oswald, M.R., and Pollefeys, M. (2022, January 18–24). Nice-slam: Neural implicit scalable encoding for slam. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.
2. ADR-MVSNet: A cascade network for 3D point cloud reconstruction with pixel occlusion;Li;Pattern Recognit.,2022
3. Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomy;Fernandes;Inf. Fusion,2021
4. Point cloud processing software solutions;Kecman;AGG+ J. Archit. Civ. Eng. Geod. Relat. Sci. Fields,2020
5. Quach, M., Valenzise, G., and Dufaux, F. (2019, January 22–25). Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression. Proceedings of the 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan.