This is the official implementation of "PG-RCNN: Semantic Surface Point Generation for 3D Object Detection" (ICCV 2023).
[ArXIv]
Thanks to OpenPCDet, our implementation is based of pcdet v0.5.2.
The results are the 3D detection performance of moderate difficulty on the val set of KITTI dataset.
| training time | Car@R40 | Pedestrian@R40 | Cyclist@R40 | download | |
|---|---|---|---|---|---|
| PGRCNN | ~4.5 hours | 85.25 | 58.37 | 75.04 | model-8.8M |
Note that the performance may vary a little due to sampling in PointNet++ encoder.
Please refer to INSTALL.md for the installation of OpenPCDet.
To train PG-RCNN, You need to additionally install pytorch3d for utilizing Chamfer Distance.
We recommend using pytorch3d ver0.7.0.
Please refer to GETTING_STARTED.md to learn more usage about this project.
Under pcdet directory, execute:
python -m pcdet.datasets.multifindbestfitPG-RCNN is released under the Apache 2.0 license.
We would like to thank the authors of OpenPCDet and BtcDet for their open source release of their codebase.