Model card for pointgpt-l.labeled-hybrid.guangyan-chen

A PointGPT point cloud classification model (autoregressive generative pretraining transformer). Trained on LabeledHybrid.

Model Details

• Model Type: Point cloud classification
• Model Stats:
  • Params (M): 360.4
  • Classes: 87
  • Features: 2048
• Dataset: LabeledHybrid
• Paper: PointGPT: Auto-regressively Generative Pre-training from Point Clouds
• Converted from: CGuangyan-BIT/PointGPT (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(
    "pointgpt-l.labeled-hybrid.guangyan-chen",
    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),
}
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():
    embeddings = model.forward_features(data.get("x"), data["pos"], data["batch"])

model.reset_classifier(num_classes=0)
with torch.no_grad():
    embeddings = model(data.get("x"), data["pos"], data["batch"])  # (B, 2048)

Citation

@inproceedings{chen2023pointgpt,
  title   = {PointGPT: Auto-regressively Generative Pre-training from Point Clouds},
  author  = {Guangyan Chen and Meiling Wang and Yi Yang and Kai Yu and Li Yuan and Yufeng Yue},
  booktitle = {NeurIPS},
  year    = {2023}
}

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