3D Representations
PointNet
Introduced by Qi et al. in PointNet: Deep Learning on Point Sets for 3D Classification and SegmentationPointNet provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. It directly takes point clouds as input and outputs either class labels for the entire input or per point segment/part labels for each point of the input.
Source: Qi et al.
Image source: Qi et al.
Source: PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Semantic Segmentation | 29 | 7.82% |
| Object Detection | 27 | 7.28% |
| 3D Object Detection | 21 | 5.66% |
| Point Cloud Classification | 16 | 4.31% |
| General Classification | 14 | 3.77% |
| Autonomous Driving | 13 | 3.50% |
| Point Cloud Segmentation | 13 | 3.50% |
| Classification | 11 | 2.96% |
| 3D Point Cloud Classification | 11 | 2.96% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
