Abstract
Real-world point clouds usually suffer from incompleteness and display different poses. While current point cloud completion methods excel in reproducing complete point clouds with consistent poses as seen in the training set, their performance tends to be unsatisfactory when handling point clouds with diverse poses. We propose a network named Rotation-Invariant Completion Network (RICNet), which consists of two parts: a Dual Pipeline Completion Network (DPCNet) and an enhancing module. Firstly, DPCNet generates a coarse complete point cloud. The feature extraction module of DPCNet can extract consistent features, no matter if the input point cloud has undergone rotation or translation. Subsequently, the enhancing module refines the fine-grained details of the final generated point cloud. RICNet achieves better rotation invariance in feature extraction and incorporates structural relationships in man-made objects. To assess the performance of RICNet and existing methods on point clouds with various poses, we applied random transformations to the point clouds in the MVP dataset and conducted experiments on them. Our experiments demonstrate that RICNet exhibits superior completion performance compared to existing methods.
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
Qi, C.R., Su, H., Mo, K., et al.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652–660 (2017)
Yuan, W., Khot, T., Held, D., et al.: Pcn: point completion network. In: International Conference on 3D Vision (3DV), pp. 728–737 (2018)
Liu, M., Sheng, L., Yang, S., et al.: Morphing and sampling network for dense point cloud completion. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11596–11603 (2020)
Pan, L.: Ecg: edge-aware point cloud completion with graph convolution. In: IEEE Robotics and Automation Letters (2020)
Wang, X., Ang, M.H., Jr., Lee, G.H.: Cascaded refinement network for point cloud completion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 790–799 (2020)
Tchapmi, L.P., Kosaraju, V., Rezatofighi, H., et al.: Topnet: structural point cloud decoder. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 383–392 (2019)
Pan, L., Chen, X., Cai, Z., et al.: Variational relational point completion network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8524–8533 (2022)
Zheng, C., Cham, T.-J., Cai, J.: Pluralistic image completion. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1438–1447 (2019)
Qi, C.R., Yi, L., Su, H., et al.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems, pp. 5105–5114 (2017)
Tombari, F., Salti, S., Di Stefano, L.: Unique signatures of histograms for local surface description. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6313, pp. 356–369. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15558-1_26
Zhang, Z., Hua, B..S, Rosen, D.W., et al.: Rotation invariant convolutions for 3d point clouds deep learning. In: International Conference on 3D Vision, pp. 204–213 (2019)
Zhang, Z., Hua, B.S., Chen, W., et al.: Global context aware convolutions for 3d point cloud understanding. In: International Conference on 3D Vision, pp. 210–219 (2020)
Kim, S., Park, J., et al.: Rotation-invariant local-to-global representation learning for 3d point cloud. In: Advances in Neural Information Processing Systems, pp. 8174–8185 (2020)
Thomas, H.: Rotation-invariant point convolution with multiple equivariant alignments. In: 2020 International Conference on 3D Vision (3DV), pp. 504–513 (2020)
Li, X., Li, et al.: A rotation-invariant framework for deep point cloud analysis. IEEE Trans. Visualizat. Comput. Graph. 4503–4514 (2021)
Zhang, Z., Hua, S.K.: RIConv++: effective rotation invariant convolutions for 3D point clouds deep learning. Inter. J. Comput. Vis. 1228–1243 (2022)
Wang, Y., Sun, Y., et al.: Dynamic graph cnn for learning on point clouds. ACM Trans. Graph. 1–12 (2019)
Knapitsch, A., Park, J., Zhou, Q., et al.: Tanks and temples: benchmarking large-scale scene reconstruction. ACM Trans. Graph. (ToG), 1–13 (2017)
Tatarchenko, M., Richter, S.R., Ranftl, R., et al.: What do single-view 3d reconstruction networks learn? In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3405–3414 (2019)
Chen, B., Fan, J., Zhao, P., et al.: Slice sequential network: a lightweight unsupervised point cloud completion network. In: Pattern Recognition and Computer Vision: 4th Chinese Conference, PRCV 2021, pp. 103–114 (2021)
Tao, M., Zhao, C., Wang, J., et al.: Global patch cross-attention for point cloud analysis. In: Pattern Recognition and Computer Vision: 5th Chinese Conference, PRCV 2022, pp. 96–111 (2022)
Pan, L., Chen, X., Cai, Z., et al.: Variational relational point completion network for robust 3D classification. IEEE Trans. Pattern Anal. Mach. Intell. (2023)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, Y., Shi, P. (2024). Rotation-Invariant Completion Network. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14426. Springer, Singapore. https://doi.org/10.1007/978-981-99-8432-9_10
Download citation
DOI: https://doi.org/10.1007/978-981-99-8432-9_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8431-2
Online ISBN: 978-981-99-8432-9
eBook Packages: Computer ScienceComputer Science (R0)