Stratified Transformer for 3D Point Cloud Segmentation

Citations Over TimeTop 1% of 2022 papers

Abstract

3D point cloud segmentation has made tremendous progress in recent years. Most current methods focus on aggregating local features, but fail to directly model long-range dependencies. In this paper, we propose Stratified Transformer that is able to capture long-range contexts and demonstrates strong generalization ability and high performance. Specifically, we first put forward a novel key sampling strategy. For each query point, we sample nearby points densely and distant points sparsely as its keys in a stratified way, which enables the model to enlarge the effective receptive field and enjoy long-range contexts at a low computational cost. Also, to combat the challenges posed by irregular point arrangements, we propose first-layer point embedding to aggregate local information, which facilitates convergence and boosts performance. Besides, we adopt contextual relative position encoding to adaptively capture position information. Finally, a memory-efficient implementation is introduced to overcome the issue of varying point numbers in each window. Extensive experiments demonstrate the effectiveness and superiority of our method on S3DIS, ScanNetv2 and ShapeNetPart datasets. Code is available at https://github.com/dvlab-research/Stratified-Transformer.

Related Papers

• → Point clouds segmentation as base for as-built BIM creation(2015)48 cited
• → TUM-FAÇADE: REVIEWING AND ENRICHING POINT CLOUD BENCHMARKS FOR FAÇADE SEGMENTATION(2022)12 cited
• → Segmentation of unorganized point cloud from terrestrial laser scanner in urban region(2010)1 cited
• → Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labels(2020)29 cited
• → Contrastive Boundary Learning for Point Cloud Segmentation(2022)10 cited