Exploiting Topological Priors for Boosting Point Cloud Generation
DOI:
https://doi.org/10.62051/6csenv07Keywords:
SP-GAN; generative adversarial network; point cloud generation; clustering.Abstract
This paper presents an innovative enhancement to the Sphere as Prior Generative Adversarial Network (SP-GAN) model, a state-of-the-art GAN designed for point cloud generation. A novel method is introduced for point cloud generation that elevates the structural integrity and overall quality of the generated point clouds by incorporating topological priors into the training process of the generator. Specifically, this work utilizes the K-means algorithm to segment a point cloud from the repository into clusters and extract centroids, which are then used as priors in the generation process of the SP-GAN. Furthermore, the discriminator component of the SP-GAN utilizes the identical point cloud that contributed the centroids, ensuring a coherent and consistent learning environment. This strategic use of centroids as intuitive guides not only boosts the efficiency of global feature learning but also substantially improves the structural coherence and fidelity of the generated point clouds. By applying the K-means algorithm to generate centroids as the prior, the work intuitively and experimentally demonstrates that such a prior enhances the quality of generated point clouds.
Downloads
References
Nießner, Matthias, Michael Zollhöfer, Shahram Izadi, and Marc Stamminger. Real-time 3D reconstruction at scale using voxel hashing. ACM Transactions on Graphics, 2013, 32(6): 1-11. DOI: https://doi.org/10.1145/2508363.2508374
Li, Ruihui, Xianzhi Li, Ka-Hei Hui, and Chi-Wing Fu. SP-GAN: Sphere-guided 3D shape generation and manipulation. ACM Transactions on Graphics, 2021, 40(4): 1-12. DOI: https://doi.org/10.1145/3476576.3476732
Wu, Chengzhi, Junwei Zheng, Julius Pfrommer, and Jürgen Beyerer. Attention-based Part Assembly for 3D Volumetric Shape Modeling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 2716-2725. DOI: https://doi.org/10.1109/CVPRW59228.2023.00272
Jangid, Devendra K., Neal R. Brodnik, Amil Khan, McLean P. Echlin, Tresa M. Pollock, Sam Daly, and B. S. Manjunath. 3DMaterialGAN: Learning 3D Shape Representation from Latent Space for Materials Science Applications. ArXiv Preprint, 2020: 2007.13887.
Lu, Dening, Qian Xie, Mingqiang Wei, Kyle GAO, Linlin Xu, and Jonathan Li. Transformers in 3d point clouds: A survey. ArXiv Preprint, 2022: 2205.07417.
Wang, Lei, Yuchun Huang, Yaolin Hou, Shenman Zhang, and Jie Shan. Graph attention convolution for point cloud semantic segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019: 10296-10305. DOI: https://doi.org/10.1109/CVPR.2019.01054
Ioannidou, Anastasia, Elisavet Chatzilari, Spiros Nikolopoulos, and Ioannis Kompatsiaris. Deep learning advances in computer vision with 3d data: A survey. ACM computing surveys, 2017, 50(2): 1-38. DOI: https://doi.org/10.1145/3042064
Shu, Dong Wook, Sung Woo Park, and Junseok Kwon. 3d point cloud generative adversarial network based on tree structured graph convolutions. In Proceedings of the IEEE/CVF international conference on computer vision, 2019: 3859-3868.
Kim, Jaeyeon, Binh-Son Hua, Thanh Nguyen, and Sai-Kit Yeung. Pointinverter: Point cloud reconstruction and editing via a generative model with shape priors. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023: 592-601. DOI: https://doi.org/10.1109/WACV56688.2023.00066
Mao, Xudong, Qing Li, Haoran Xie, Raymond YK Lau, Zhen Wang, and Stephen Paul Smolley. Least squares generative adversarial networks. In Proceedings of the IEEE international conference on computer vision, 2017: 2794-2802. DOI: https://doi.org/10.1109/ICCV.2017.304
Shu, Dong Wook, Sung Woo Park, and Junseok Kwon. 3d point cloud generative adversarial network based on tree structured graph convolutions. In Proceedings of the IEEE/CVF international conference on computer vision, 2019: 3859-3868. DOI: https://doi.org/10.1109/ICCV.2019.00396
Achlioptas, Panos, Olga Diamanti, Ioannis Mitliagkas, and Leonidas Guibas. Learning representations and generative models for 3d point clouds." In International conference on machine learning, 2018: 40-49.
Heusel, Martin, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 2017, 30: 1-12.
Kullback, Solomon, and Richard A. Leibler. On information and sufficiency. The annals of mathematical statistics, 1951, 22(1): 79-86. DOI: https://doi.org/10.1214/aoms/1177729694
Downloads
Published
Conference Proceedings Volume
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
