Abstract
In 2D image domain, recent researches have made significant progress in encoding context information for instance segmentation. While the counterpart in point cloud is still left far behind. Previous works mostly focus on leveraging semantic information and aggregating point local information through K-Nearest-Neighbor method. Such methods are unaware of object boundary information which is important to separating nearby objects. We propose a novel module to integrate object bounding box information into embedding for Point Cloud Instance Segmentation. The proposed module called Object Bounding Box-aware module (OBAM) boosts the instance segmentation performance by encoding Object Bounding Box information. Through attention mechanism, the module removes redundant boundary information. Comprehensive experiments on two popular benchmarks (S3DIS and ScanNetV2) show the effectiveness of our method. Our method achieves the State-of-the-art instance segmentation performance on S3DIS benchmark.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Armeni, I., et al.: IEEE: 3D semantic parsing of large-scale indoor spaces. In: Computer Vision & Pattern Recognition (2016)
Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Niener, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes (2017)
Graham, B., Engelcke, M., Maaten, L.: 3D semantic segmentation with submanifold sparse convolutional networks. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Hu, Q., Yang, B., Xie, L., Rosa, S., Markham, A.: RandLA-Net: efficient semantic segmentation of large-scale point clouds. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)
Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017
Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: NIPS, pp. 5105–5114 (2017)
Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. (2002)
Riegler, G., Ulusoy, A.O., Geiger, A.: OctNet: learning deep 3D representations at high resolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3D shape recognition. IEEE (2015)
He, T., Liu, Y., Shen, C., Wang, X., Sun, C.: Instance-aware embedding for point cloud instance segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 255–270. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58577-8_16
Wang, W., Yu, R., Huang, Q., Neumann, U.: SGPN: similarity group proposal network for 3D point cloud instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018
Wang, X., Liu, S., Shen, X., Shen, C., Jia, J.: Associatively segmenting instances and semantics in point clouds. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Yang, B., et al.: Learning object bounding boxes for 3D instance segmentation on point clouds. In: Advances in Neural Information Processing Systems, pp. 6737–6746 (2019)
Yaw, H.: The Hungarian method for the assignment problem. Naval Res. Logist. Q. 2, 83–97(1955)
Zhao, L., Tao, W.: JSNet: joint instance and semantic segmentation of 3D point clouds. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 7, pp. 12951–12958 (2020)
He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), October 2017
Mo, K., Zhu, S., Chang, A.X., Li, Y., Hao, S.: PartNet: a large-scale benchmark for fine-grained and hierarchical part-level 3D object understanding. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Acknowledgement
The research is funded by National Natural Science Foundation of China (No. 61972157), National Key Research and Development Program of China (No. 2019YFC1521104) and Shanghai Municipal Science and Technology Major Project (2021SHZDZX0102).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Cheng, L., Yang, T., Ma, L. (2021). Object Bounding Box-Aware Embedding for Point Cloud Instance Segmentation. In: Pham, D.N., Theeramunkong, T., Governatori, G., Liu, F. (eds) PRICAI 2021: Trends in Artificial Intelligence. PRICAI 2021. Lecture Notes in Computer Science(), vol 13033. Springer, Cham. https://doi.org/10.1007/978-3-030-89370-5_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-89370-5_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89369-9
Online ISBN: 978-3-030-89370-5
eBook Packages: Computer ScienceComputer Science (R0)