pointrcnn.kitti.openpcdet

Model card for pointrcnn.kitti.openpcdet

A PointRCNN 3D object detection model (two-stage point-based proposal and refinement). Trained on KITTI.

Model Details

• Model Type: 3D object detection
• Model Stats:
  • Params (M): 4.0
  • Input channels: 4
  • Classes: 3
  • Features: 128
• Dataset: KITTI
• Metrics: mAP 69.29, AP/Car 78.67, AP/Pedestrian 56.94, AP/Cyclist 72.27 (reference 68.41)
• Paper: PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
• Converted from: open-mmlab/OpenPCDet (Apache-2.0)
• Library: torch-pointcloud

Install

pip install torch-pointcloud

Usage

import torch
import torch_pointcloud as tp
from torch_pointcloud.utils.data import collate

model, info = tp.create_model(
    "pointrcnn.kitti.openpcdet",
    pretrained=True,
    return_info=True,
)
model = model.eval()

# synthetic sample with the keys a dataset provides
num_points = 8192
sample = {
    "pos": torch.randn(num_points, 3),
    "intensity": torch.rand(num_points, 1),
}
data = info["transform"](sample)
data = collate([data])

with torch.no_grad():
    out = model(data.get("x"), data["pos"], data["batch"])

Feature extraction

with torch.no_grad():
    features = model.forward_features(data.get("x"), data["pos"], data["batch"])  # 128 channels

Citation

@inproceedings{shi2019pointrcnn,
  title   = {PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud},
  author  = {Shaoshuai Shi and Xiaogang Wang and Hongsheng Li},
  booktitle = {CVPR},
  year    = {2019}
}

@inproceedings{geiger2012kitti,
  title     = {Are we ready for Autonomous Driving? The {KITTI} Vision Benchmark Suite},
  author    = {Geiger, Andreas and Lenz, Philip and Urtasun, Raquel},
  booktitle = {CVPR},
  year      = {2012}
}

@software{dujardin2026pytorchpointcloud,
  author  = {Arthur Dujardin},
  title   = {PyTorch PointCloud},
  year    = {2026},
  doi     = {10.5281/zenodo.22159632},
  url     = {https://github.com/arthurdjn/pytorch-pointcloud},
}