PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention
Name
1810.05591.pdf
Description
Accepted version
Size
6.16 MB
Format
Adobe PDF
Checksum (MD5)
5798caa0015776d95833afd075d6b01a
Author(s)
Sun, Yongbin
Wang, Yue
Liu, Ziwei
Siegel, Joshua E
Sarma, Sanjay E
Date Issued
March 2020
Journal
Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
Publisher
IEEE
Citation
Sun, Yongbin, Wang, Yue, Liu, Ziwei, Siegel, Joshua E and Sarma, Sanjay E. 2020. "PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention." Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020.
Version
Author's final manuscript
Abstract
© 2020 IEEE. Generating 3D point clouds is challenging yet highly desired. This work presents a novel autoregressive model, PointGrow, which can generate diverse and realistic point cloud samples from scratch or conditioned on semantic contexts. This model operates recurrently, with each point sampled according to a conditional distribution given its previously-generated points, allowing inter-point correlations to be well-exploited and 3D shape generative processes to be better interpreted. Since point cloud object shapes are typically encoded by long-range dependencies, we augment our model with dedicated self-attention modules to capture such relations. Extensive evaluations show that PointGrow achieves satisfying performance on both unconditional and conditional point cloud generation tasks, with respect to realism and diversity. Several important applications, such as unsupervised feature learning and shape arithmetic operations, are also demonstrated.
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/wacv45572.2020.9093430
