Model card for tr3d.scannet.mmdet3d

A TR3D 3D object detection model (fast fully convolutional sparse voxel detector). Trained on ScanNet.

Model Details

• Model Type: 3D object detection
• Model Stats:
  • Params (M): 14.7
  • Input channels: 3
  • Classes: 18
  • Features: 128
• Dataset: ScanNet
• Metrics: mAP@0.25 71.98, mAP@0.5 58.57
• Paper: TR3D: Towards Real-Time Indoor 3D Object Detection
• Converted from: open-mmlab/mmdetection3d (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(
    "tr3d.scannet.mmdet3d",
    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),
    "color": torch.rand(num_points, 3) * 255,
}
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"])  # 128 channels

Citation

@inproceedings{rukhovich2023tr3d,
  title   = {{TR3D}: Towards Real-Time Indoor 3D Object Detection},
  author  = {Danila Rukhovich and Anna Vorontsova and Anton Konushin},
  booktitle = {ICIP},
  year    = {2023}
}

@inproceedings{dai2017scannet,
  title   = {ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes},
  author  = {Angela Dai and Angel X. Chang and Manolis Savva and Maciej Halber and Thomas Funkhouser and Matthias Nießner},
  booktitle = {CVPR},
  year    = {2017}
}

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