Model card for lion-mamba.nuscenes.zhe-liu

A LION 3D object detection model (linear group RNN detector over voxel windows). Trained on nuScenes.

Model Details

• Model Type: 3D object detection
• Model Stats:
  • Params (M): 16.1
  • Input channels: 5
  • Classes: 10
  • Features: 384
• Dataset: nuScenes
• Paper: LION: Linear Group RNN for 3D Object Detection in Point Clouds
• Converted from: happinesslz/LION (Apache-2.0)
• Library: torch-pointcloud

Install

pip install torch-pointcloud

This checkpoint also needs spconv and mamba-ssm, which need 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(
    "lion-mamba.nuscenes.zhe-liu",
    task="detection",
    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])
data = {key: value.cuda() for key, value in data.items()}

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"])  # 384 channels

Citation

@inproceedings{liu2024lion,
  title   = {LION: Linear Group RNN for 3D Object Detection in Point Clouds},
  author  = {Zhe Liu and Jinghua Hou and Xinyu Wang and Xiaoqing Ye and Jingdong Wang and Hengshuang Zhao and Xiang Bai},
  booktitle = {NeurIPS},
  year    = {2024}
}

@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},
}