Artificial Intelligence in Point Cloud Compression
DOI:
https://doi.org/10.62051/ijcsit.v4n2.03Keywords:
3D point cloud, Artificial intelligence, Compression algorithm, 3D convolutionAbstract
Point cloud is a data representation of a three-dimensional object or scene. It is created by collecting a large number of spatial coordinate points, which are used to discretely represent the surface information of a three-dimensional object. Compared to traditional two-dimensional images, point clouds are particularly suited to the presentation of three-dimensional models and geospatial information. They have had a significant impact on the development of smart cities, autonomous driving applications, and augmented reality technology. However, due to the irregularity, disorganisation, diversity and other shortcomings of the point cloud, the traditional point cloud compression faces significant challenges. This paper will review the traditional coding methods and focus on the current cutting-edge artificial intelligence technology to bring the point cloud compression advances. It will also consider the future development direction.
Downloads
References
[1] MPEG 3DGC. (2020). G-PCC codec description v9. In International Organization for Standardization Meeting Document ISO/IEC JTC1/SC29/WG7 MPEG/N0011.
[2] MPEG 3DGC. (2020). V-PCC codec description v12. In International Organization for Standardization Meeting Document ISO/IEC JTC1/SC29/WG7 MPEG/N0012.
[3] Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. In Proceedings of the AAAI Conference on Artificial Intelligence, 31(1).
[4] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. Las Vegas, NV, USA. pp. 770-778.
[5] Guarda, A. F., Rodrigues, N. M., & Pereira, F. (2019). Point cloud coding: Adopting a deep learning-based approach. In 2019 Picture Coding Symposium (PCS). pp. 1-5.
[6] Wang, J., Ding, D., Li, Z., & Ma, Z. (2021). Multiscale point cloud geometry compression. In 2021 Data Compression Conference (DCC). pp. 73-82.
[7] Fu, C., Li, G., Song, R., Gao, W., & Liu, S. (2022) Octattention: Octree-based large-scale contexts model for point cloud compression." In Proceedings of the AAAl. 36(1).
[8] Chen, Z., Qian, Z., Wang, S., & Chen, Q. (2022). Point cloud compression with sibling context and surface priors. In S. Avidan, G. Brostow, M. Cissé, G. M. Farinella, & T. Hassner (Eds.), Computer Vision – ECCV 2022 . ECCV 2022. Lecture Notes in Computer Science, vol. 13698.
[9] He, Y., Ren, X., Tang, D., Zhang, Y., Xue, X., & Fu, Y. (2022). Density-preserving deep point cloud compression. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 2333-2342 .
[10] Zhang, J., Liu, G., Ding, D., & Ma, Z. (2022). Transformer and upsampling-based point cloud compression. In Proceedings of the 1st International Workshop on Advances in Point Cloud Compression, Processing, and Analysis. pp. 33-39.
[11] X. Li, O. A. Hanna, C. Fragouli, S. Diggavi, G. Verma and J. Bhattacharyya. (2023) "Feature Compression for Multimodal Multi-Object Tracking," MILCOM 2023 - 2023 IEEE Military Communications Conference (MILCOM). Boston, MA, USA. pp. 139-143.
[12] Z. Yu, L. Zhang, S. Li, Y. Zhang and X. Ning. (2021) "2D-3DMatchingNet: Multimodal Point Completion with 2D Geometry Matching," 2021 International Conference on High Performance Big Data and Intelligent Systems (HPBD&IS). Macau, China. pp. 94-99.
[13] Charles, R. Q., Su, H., Mo, K., & Guibas, L. J. (2017). PointNet: Deep learning on point sets for 3D classification and segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA. pp. 77-85.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
