.png){kind=icon}
.png){kind=icon}
Return
Context-Aware 3D Point Cloud Semantic Segmentation With Plane Guidance
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2022.3212914.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Point cloud segmentation is fundamental in understanding 3D environments. However, most existing methods usually perform poorly on identifying boundaries of touching objects and large surfaces of objects. Planes in a scene usually act as supporting surfaces to separate touching objects and provide geometry priors to group points on a large surface as shown in Fig. 1. Besides, planes can roughly represent the structure of a scene, and are more efficient to encode holistic scene contexts than large scale point clouds. In light of the above advantages, we advise a plane-assisted module, coined 3D-PAM, to enhance semantic segmentation of touching objects and large surface objects. 3D-PAM consists of a plane separation network (PS-Net) and a plane relation network (PR-Net). PS-Net focuses on learning features that can robustly separate touching objects, e.g., a chair on a floor, as well as capture plane-based geometry priors to group points on a large plane, e.g., points of a desk. PR-Net encodes mutual plane relations as a proxy of a scene structure to capture holistic contexts. 3D-PAM is designed as a plug-and-play module so that it can be easily plugged into any off-the-shelf semantic segmentation network. Extensive experiments demonstrate that the method achieves large segmentation improvements on several backbones, and accomplishes superior results on most categories when using a RandLA-Net backbone (11/13 categories on S3DIS dataset and 15/20 categories on ScanNetv2 dataset). The project is available at GitHub https://github.com/windmillknight/ Context- Aware- 3DPoint- Cloud- Semantic-Segmentation-With- Plane- Guidance
Keywords:
Three-dimensional displays
Point cloud compression
Geometry
Shape
Semantics
Task analysis
Network architecture
3D semantic segmentation
holistic contexts
point cloud
plane geometry
Journal
IF:
9.7
Papers:
4.5K
Citations:
2.4W