MSG-Point-GAN: Multi-Scale Gradient Point GAN for Point Cloud Generation
Author:
Wang Bingxu1ORCID, Lan Jinhui1, Gao Jiangjiang1
Affiliation:
1. School of Automation, University of Science and Technology Beijing, 30 Xueyuan Road, Haidian District, Beijing 100083, China
Abstract
The generative adversarial network (GAN) has recently emerged as a promising generative model. Its application in the image field has been extensive, but there has been little research concerning point clouds.The combination of a GAN and a graph convolutional network has been the state-of-the-art method for generating point clouds. However, there is a significant gap between the generated point cloud and the point cloud used for training. In order to improve the quality of the generated point cloud, this study proposed multi-scale gradient point GAN (MSG-Point-GAN). The training of the GAN is a dynamic game process, and we expected the generation and discrimination capabilities to be symmetric, so that the network training would be more stable. Based on the concept of progressive growth, this method used the network structure of a multi-scale gradient GAN (MSG-GAN) to stabilize the training process. The discriminator of this method used part of the PointNet structure to resolve the problem of the disorder and rotation of the point cloud. The discriminator could effectively determine the authenticity of the generated point cloud. This study also analyzed the optimization process of the objective function of the MSG-Point-GAN. The experimental results showed that the training process of the MSG-Point-GAN was stable, and the point cloud quality was superior to other methods in subjective vision. From the perspective of performance metrics, the gap between the point cloud generated by the proposed method and the real point cloud was significantly smaller than that generated by other methods. Based on the practical analysis, the point cloud generated by the proposed method for training the point-cloud classification network was improved by about 0.2%, as compared to the original network. The proposed method provided a stable training framework for point cloud generation. It can effectively promote the development of point-cloud-generation technology.
Funder
13th Five-Year Plan Funding of China Fundamental Research Program
Subject
Physics and Astronomy (miscellaneous),General Mathematics,Chemistry (miscellaneous),Computer Science (miscellaneous)
Reference26 articles.
1. Goodfellow, I. (2014, January 8–13). Generative adversarial nets. Proceedings of the Neural Information Processing Systems Conference, Montreal, QC, Canada. 2. Khan, S.U.U., Al-Sabri, E.H.A.A., Ismail, R., Mohammed, M.M.S., Hussain, S., and Mehmood, A. (2023). Prediction Model of a Generative Adversarial Network Using the Concept of Complex Picture Fuzzy Soft Information. Symmetry, 15. 3. Shao, C., Li, X., Li, F., and Zhou, Y. (2022). Large Mask Image Completion with Conditional GAN. Symmetry, 14. 4. Wu, J., Zhang, C., and Xue, T. (2017). Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling. arXiv. 5. Progressive conditional GAN-based augmentation for 3D object recognition;Muzahid;Neurocomputing,2021
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|