Model card for randlanet.s3dis-area3.open3d

A RandLA-Net point cloud semantic segmentation model (random sampling with local feature aggregation). Trained on S3DIS (Area 3).

Model Details

• Model Type: Point cloud semantic segmentation
• Model Stats:
  • Params (M): 5.0
  • Input channels: 6
  • Classes: 13
  • Features: 32
• Dataset: S3DIS (Area 3)
• Metrics: mIoU 70.43, OA 87.9
• Paper: RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
• Converted from: isl-org/Open3D-ML (MIT)
• 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(
    "randlanet.s3dis-area3.open3d",
    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),
    "color": torch.rand(num_points, 3) * 255,
    "segment": torch.zeros(num_points, dtype=torch.long),
    "instance": torch.zeros(num_points, dtype=torch.long),
}
data = info["transform"](sample)
data = collate([data])

with torch.no_grad():
    logits = 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"])

model.reset_classifier(num_classes=0)
with torch.no_grad():
    features = model(data.get("x"), data["pos"], data["batch"])  # (N, 32)

Citation

@inproceedings{hu2020randlanet,
  title   = {RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds},
  author  = {Qingyong Hu and Bo Yang and Linhai Xie and Stefano Rosa and Yulan Guo and Zhihua Wang and Niki Trigoni and Andrew Markham},
  booktitle = {CVPR},
  year    = {2020}
}

@inproceedings{armeni2016s3dis,
  title     = {{3D} Semantic Parsing of Large-Scale Indoor Spaces},
  author    = {Armeni, Iro and Sener, Ozan and Zamir, Amir R. and Jiang, Helen and Brilakis, Ioannis and Fischer, Martin and Savarese, Silvio},
  booktitle = {CVPR},
  year      = {2016}
}

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