voxelnext.nuscenes.openpcdet

Model card for voxelnext.nuscenes.openpcdet

A VoxelNeXt 3D object detection model (fully sparse voxel detector). Trained on nuScenes.

Model Details

• Model Type: 3D object detection
• Model Stats:
  • Params (M): 8.0
  • Input channels: 5
  • Classes: 10
  • Features: 128
• Dataset: nuScenes
• Metrics: mAP 61.2, NDS 66.81
• Paper: VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking
• Converted from: open-mmlab/OpenPCDet (Apache-2.0)
• Library: torch-pointcloud

Install

pip install torch-pointcloud

This checkpoint also needs spconv, which needs a build matching your torch and CUDA: see the installation guide.

Usage

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

model, info = tp.create_model(
    "voxelnext.nuscenes.openpcdet",
    pretrained=True,
    return_info=True,
)
model = model.cuda().eval()  # GPU-only kernels

# synthetic sample with the keys a dataset provides
num_points = 8192
sample = {
    "pos": torch.randn(num_points, 3),
    "intensity": torch.rand(num_points, 1),
    "timestamp": torch.zeros(num_points, 1),
}
data = info["transform"](sample)
data = collate([data], batch_from="pos_voxel")
data = {key: value.cuda() for key, value in data.items()}

with torch.no_grad():
    out = model(data["voxel"], data["pos_voxel"], data["voxel_num_points"], data["batch"])

Feature extraction

with torch.no_grad():
    features = model.forward_features(
        data["voxel"],
        data["pos_voxel"],
        data["voxel_num_points"],
        data["batch"],
    )  # 128 channels

Citation

@inproceedings{chen2023voxelnext,
  title   = {VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking},
  author  = {Yukang Chen and Jianhui Liu and Xiangyu Zhang and Xiaojuan Qi and Jiaya Jia},
  booktitle = {CVPR},
  year    = {2023}
}

@inproceedings{caesar2020nuscenes,
  title   = {nuScenes: A multimodal dataset for autonomous driving},
  author  = {Holger Caesar and Varun Bankiti and Alex H. Lang and Sourabh Vora and Venice Erin Liong and Qiang Xu and Anush Krishnan and Yu Pan and Giancarlo Baldan and Oscar Beijbom},
  booktitle = {CVPR},
  year    = {2020}
}

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