Placeholder chapter page. Sections are produced by the book-skills pipeline.
Sections
- 42.1 Lidar measurement principles
- 42.2 Point-cloud representations; voxelization and pillars
- 42.3 Sparse-convolution backbones (CenterPoint, VoxelNeXt)
- 42.4 Point transformers (Point Transformer v3)
- 42.5 3D detection, segmentation, and tracking
- 42.6 Self-supervised lidar pretraining (ALSO, LISO)
- 42.7 Weather, domain shift, and deployment constraints
Lab 42
build a point-cloud detection/segmentation pipeline on a public dataset subset with OpenPCDet/Pointcept.