SEGCloud: Semantic Segmentation of 3D Point Clouds
About
3D semantic scene labeling is fundamental to agents operating in the real world. In particular, labeling raw 3D point sets from sensors provides fine-grained semantics. Recent works leverage the capabilities of Neural Networks (NNs), but are limited to coarse voxel predictions and do not explicitly enforce global consistency. We present SEGCloud, an end-to-end framework to obtain 3D point-level segmentation that combines the advantages of NNs, trilinear interpolation(TI) and fully connected Conditional Random Fields (FC-CRF). Coarse voxel predictions from a 3D Fully Convolutional NN are transferred back to the raw 3D points via trilinear interpolation. Then the FC-CRF enforces global consistency and provides fine-grained semantics on the points. We implement the latter as a differentiable Recurrent NN to allow joint optimization. We evaluate the framework on two indoor and two outdoor 3D datasets (NYU V2, S3DIS, KITTI, Semantic3D.net), and show performance comparable or superior to the state-of-the-art on all datasets.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Semantic segmentation | S3DIS (Area 5) | mIOU48.92 | 799 | |
| Semantic segmentation | S3DIS (6-fold) | mIoU (Mean IoU)48.92 | 315 | |
| Scene Parsing | NYUDv2 (test) | mIoU43.5 | 35 | |
| Semantic segmentation | Semantic3D reduced-8 (test) | mIoU61.3 | 33 | |
| Semantic segmentation | Semantic3D (reduced-8) | mIoU61.3 | 30 | |
| 3D Semantic Segmentation | S3DIS (Area 5 test (Fold #1)) | mIoU48.92 | 19 | |
| Semantic segmentation | S3DIS (5th fold) | Mean IoU48.92 | 19 | |
| Semantic segmentation | Semantic3D reduced v1 (test) | Mean IoU61.3 | 18 | |
| Semantic segmentation | KITTI (test) | mIoU17.5 | 16 | |
| Semantic segmentation | NYUv2 13-class labeling | -- | 12 |