PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention
2020 IEEE Winter Conference on Applications of Computer Vision (WACV)(2020)
摘要
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.
更多查看译文
关键词
PointGrow,autoregressively learned point cloud generation,conditional distribution,point cloud object shapes,self-attention modules,unsupervised feature learning,shape arithmetic operations,3D point cloud generation,3D shape generative model,3D shape recognition,deep networks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络