Learning to Segment 3D Point Clouds in 2D Image Space
This addresses the challenge of efficient 3D point cloud segmentation for computer vision applications, offering a novel approach that is incremental in leveraging existing 2D techniques.
The paper tackles the problem of segmenting 3D point clouds by projecting them into 2D image space to apply traditional 2D CNNs, achieving state-of-the-art performance on ShapeNet and PartNet with significant improvements over existing methods.
In contrast to the literature where local patterns in 3D point clouds are captured by customized convolutional operators, in this paper we study the problem of how to effectively and efficiently project such point clouds into a 2D image space so that traditional 2D convolutional neural networks (CNNs) such as U-Net can be applied for segmentation. To this end, we are motivated by graph drawing and reformulate it as an integer programming problem to learn the topology-preserving graph-to-grid mapping for each individual point cloud. To accelerate the computation in practice, we further propose a novel hierarchical approximate algorithm. With the help of the Delaunay triangulation for graph construction from point clouds and a multi-scale U-Net for segmentation, we manage to demonstrate the state-of-the-art performance on ShapeNet and PartNet, respectively, with significant improvement over the literature. Code is available at https://github.com/Zhang-VISLab.