Point Cloud Learning with Transformer
This work addresses the challenge of processing irregular 3D point clouds for computer vision applications, representing an incremental advancement by adapting transformer architectures from NLP to this domain.
The paper tackles 3D point cloud representation learning by introducing a Multi-level Multi-scale Point Transformer (MLMSPT) framework that directly processes irregular point clouds, achieving competitive performance on public benchmark datasets for 3D shape classification and segmentation tasks.
Remarkable performance from Transformer networks in Natural Language Processing promote the development of these models in dealing with computer vision tasks such as image recognition and segmentation. In this paper, we introduce a novel framework, called Multi-level Multi-scale Point Transformer (MLMSPT) that works directly on the irregular point clouds for representation learning. Specifically, a point pyramid transformer is investigated to model features with diverse resolutions or scales we defined, followed by a multi-level transformer module to aggregate contextual information from different levels of each scale and enhance their interactions. While a multi-scale transformer module is designed to capture the dependencies among representations across different scales. Extensive evaluation on public benchmark datasets demonstrate the effectiveness and the competitive performance of our methods on 3D shape classification, segmentation tasks.