This is the official code of the paper PointGPT: Auto-regressively Generative Pre-training from Point Clouds
In this work, we present PointGPT, a novel approach that extends the concept of GPT to point clouds, utilizing a point cloud auto-regressive generation task for pre-training transformer models. In object classification tasks, our PointGPT achieves 94.9% accuracy on the ModelNet40 dataset and 93.4% accuracy on the ScanObjectNN dataset, outperforming all other transformer models. In few-shot learning tasks, our method also attains new SOTA performance on all four benchmarks.
The code will be released soon!