Learning to Segment 3D Point Clouds in 2D Image Space

12 Mar 2020Yecheng LyuXinming HuangZiming Zhang

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... (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
3D Part Segmentation ShapeNet-Part Learning to Segment 3D Point Clouds in 2D Image Space Class Average IoU 84.6 # 2
Instance Average IoU 88.8 # 2