CPCGAN: A Controllable 3D Point Cloud Generative Adversarial Network with Semantic Label Generating
Abstract
Generative Adversarial Networks (GAN) are good at generating variant samples of complex data distributions. Generating a sample with certain properties is one of the major tasks in the real-world application of GANs. In this paper, we propose a novel generative adversarial network to generate 3D point clouds from random latent codes, named Controllable Point Cloud Generative Adversarial Network(CPCGAN). A two-stage GAN framework is utilized in CPCGAN and a sparse point cloud containing major structural information is extracted as the middle-level information between the two stages. With their help, CPCGAN has the ability to control the generated structure and generate 3D point clouds with semantic labels for points. Experimental results demonstrate that the proposed CPCGAN outperforms state-of-the-art point cloud GANs.
Cite
Text
Yang et al. "CPCGAN: A Controllable 3D Point Cloud Generative Adversarial Network with Semantic Label Generating." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I4.16425Markdown
[Yang et al. "CPCGAN: A Controllable 3D Point Cloud Generative Adversarial Network with Semantic Label Generating." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/yang2021aaai-cpcgan/) doi:10.1609/AAAI.V35I4.16425BibTeX
@inproceedings{yang2021aaai-cpcgan,
title = {{CPCGAN: A Controllable 3D Point Cloud Generative Adversarial Network with Semantic Label Generating}},
author = {Yang, Ximing and Wu, Yuan and Zhang, Kaiyi and Jin, Cheng},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2021},
pages = {3154-3162},
doi = {10.1609/AAAI.V35I4.16425},
url = {https://mlanthology.org/aaai/2021/yang2021aaai-cpcgan/}
}