PCT: Point cloud transformer

The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing. This paper presents a novel framework named Point Cloud Transformer(PCT) learning. PCT is based on Transformer, which achieves huge success in natural language processing displays great potential image It inherently permutation invariant sequence points, making well-suited To better capture local context within the cloud, we enhance input embedding with support farthest sampling nearest neighbor search. Extensive experiments demonstrate that state-of-the-art performance shape classification, part segmentation normal estimation tasks.