Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/WACV45572.2020.9093430 | 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) |
Keywords | Field | DocType |
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 | Autoregressive model,Scratch,Fidelity,Conditional probability distribution,Computer science,Interpolation,Theoretical computer science,Agile software development,Artificial intelligence,Point cloud,Manifold,Machine learning | Journal |
Volume | ISSN | ISBN |
abs/1810.05591 | 2472-6737 | 978-1-7281-6554-7 |
Citations | PageRank | References |
3 | 0.39 | 10 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yongbin Sun | 1 | 244 | 9.56 |
Yue Wang | 2 | 253 | 7.65 |
Ziwei Liu | 3 | 1361 | 63.23 |
Josh Siegel | 4 | 36 | 6.04 |
Sanjay E. Sarma | 5 | 1649 | 199.90 |