Model card for ptv3-base.nuscenes.pointcept

A Point Transformer V3 point cloud semantic segmentation model (serialized neighborhood attention). Trained on nuScenes.

Model Details

• Model Type: Point cloud semantic segmentation
• Model Stats:
  • Params (M): 46.2
  • Input channels: 4
  • Classes: 16
  • Features: 64
• Dataset: nuScenes
• Metrics: mIoU 80.21, OA 94.62, simple/mIoU 78.32, simple/OA 94.25
• Paper: Point Transformer V3: Simpler, Faster, Stronger
• Converted from: Pointcept/Pointcept (MIT)
• Library: torch-pointcloud

Install

pip install torch-pointcloud

This checkpoint also needs spconv and flash-attn, 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(
    "ptv3-base.nuscenes.pointcept",
    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),
}
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_grid"], data["batch"], pos=data["pos"])

Feature extraction

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

model.reset_classifier(num_classes=0)
with torch.no_grad():
    features = model(data.get("x"), data["pos_grid"], data["batch"], pos=data["pos"])  # (N, 64)

Citation

@inproceedings{wu2024ptv3,
  title   = {Point Transformer V3: Simpler, Faster, Stronger},
  author  = {Xiaoyang Wu and Li Jiang and Peng-Shuai Wang and Zhijian Liu and Xihui Liu and Yu Qiao and Wanli Ouyang and Tong He and Hengshuang Zhao},
  booktitle = {CVPR},
  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},
}