Abstract | ||
---|---|---|
Recently, growing attention has been paid in the process of point cloud with deep learning method. It is natural to process these data hierarchical as 2D convolutional neural network(CNN) suggests, which needs to downsample the point clouds. Classic sampling approaches, such as farthest point sampling (FPS), do not consider the downstream task. Recent works showed that learning a task-specific sam... |
Year | Venue | Keywords |
---|---|---|
2021 | 2021 60th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE) | Deep learning,Instruments,Sampling methods,Convolutional neural networks,Task analysis |
DocType | ISBN | Citations |
Conference | 978-4-9077-6473-9 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |