Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds
Keywords:3D Computer Vision, Scene Analysis & Understanding, Segmentation
AbstractBoundary information plays a significant role in 2D image segmentation, while usually being ignored in 3D point cloud segmentation where ambiguous features might be generated in feature extraction, leading to misclassification in the transition area between two objects. In this paper, firstly, we propose a Boundary Prediction Module (BPM) to predict boundary points. Based on the predicted boundary, a boundary-aware Geometric Encoding Module (GEM) is designed to encode geometric information and aggregate features with discrimination in a neighborhood, so that the local features belonging to different categories will not be polluted by each other. To provide extra geometric information for boundary-aware GEM, we also propose a light-weight Geometric Convolution Operation (GCO), making the extracted features more distinguishing. Built upon the boundary-aware GEM, we build our network and test it on benchmarks like ScanNet v2, S3DIS. Results show our methods can significantly improve the baseline and achieve state-of-the-art performance.
How to Cite
Gong, J., Xu, J., Tan, X., Zhou, J., Qu, Y., Xie, Y., & Ma, L. (2021). Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1424-1432. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16232
AAAI Technical Track on Computer Vision I