torch-pointcloud/spvcnn-119gmacs.semantickitti.mit-han-lab

pip install torch-pointcloud

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

model, info = tp.create_model(
    "spvcnn-119gmacs.semantickitti.mit-han-lab",
    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),
    "segment": torch.zeros(num_points, dtype=torch.long),
    "instance": torch.zeros(num_points, dtype=torch.long),
}
data = info["transform"](sample)
data = collate([data])
data = {key: value.cuda() for key, value in data.items()}

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

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, 96)

@inproceedings{tang2020spvnas,
  title   = {Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution},
  author  = {Haotian Tang and Zhijian Liu and Shengyu Zhao and Yujun Lin and Ji Lin and Hanrui Wang and Song Han},
  booktitle = {ECCV},
  year    = {2020}
}

@inproceedings{behley2019semantickitti,
  title   = {SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences},
  author  = {Jens Behley and Martin Garbade and Andres Milioto and Jan Quenzel and Sven Behnke and Cyrill Stachniss and Juergen Gall},
  booktitle = {ICCV},
  year    = {2019}
}

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