Papers
Topics
Authors
Recent
2000 character limit reached

Concavity-Induced Distance for Unoriented Point Cloud Decomposition (2306.11051v1)

Published 19 Jun 2023 in cs.CV and cs.RO

Abstract: We propose Concavity-induced Distance (CID) as a novel way to measure the dissimilarity between a pair of points in an unoriented point cloud. CID indicates the likelihood of two points or two sets of points belonging to different convex parts of an underlying shape represented as a point cloud. After analyzing its properties, we demonstrate how CID can benefit point cloud analysis without the need for meshing or normal estimation, which is beneficial for robotics applications when dealing with raw point cloud observations. By randomly selecting very few points for manual labeling, a CID-based point cloud instance segmentation via label propagation achieves comparable average precision as recent supervised deep learning approaches, on S3DIS and ScanNet datasets. Moreover, CID can be used to group points into approximately convex parts whose convex hulls can be used as compact scene representations in robotics, and it outperforms the baseline method in terms of grouping quality. Our project website is available at: https://ai4ce.github.io/CID/

Definition Search Book Streamline Icon: https://streamlinehq.com
References (34)
  1. J. Schulman, J. Ho, A. X. Lee, I. Awwal, H. Bradlow, and P. Abbeel, “Finding locally optimal, collision-free trajectories with sequential convex optimization.” in Robotics: science and systems, vol. 9, no. 1.   Berlin, Germany, 2013, pp. 1–10.
  2. S. C. Stein, F. Wörgötter, M. Schoeler, J. Papon, and T. Kulvicius, “Convexity based object partitioning for robot applications,” in ICRA.   IEEE, 2014, pp. 3213–3220.
  3. V. Chari, A. Agrawal, Y. Taguchi, and S. Ramalingam, “Convex bricks: A new primitive for visual hull modeling and reconstruction,” in ICRA.   IEEE, 2012, pp. 770–777.
  4. S. Qin, X. Zhu, Y. Yang, and Y. Jiang, “Real-time hand gesture recognition from depth images using convex shape decomposition method,” Journal of Signal Processing Systems, vol. 74, no. 1, pp. 47–58, 2014.
  5. M. Ghosh, N. M. Amato, Y. Lu, and J.-M. Lien, “Fast approximate convex decomposition using relative concavity,” Computer-Aided Design, vol. 45, no. 2, pp. 494–504, 2013.
  6. K. Mamou, E. Lengyel, and A. Peters, “Volumetric hierarchical approximate convex decomposition,” in Game Engine Gems 3.   AK Peters, 2016, pp. 141–158.
  7. J.-M. Lien and N. M. Amato, “Approximate convex decomposition of polygons,” in Proceedings of the twentieth annual symposium on Computational geometry, 2004, pp. 17–26.
  8. S. Asafi, A. Goren, and D. Cohen-Or, “Weak convex decomposition by lines-of-sight,” in Computer graphics forum, vol. 32, no. 5.   Wiley Online Library, 2013, pp. 23–31.
  9. O. V. Kaick, N. Fish, Y. Kleiman, S. Asafi, and D. Cohen-Or, “Shape segmentation by approximate convexity analysis,” ACM Transactions on Graphics (TOG), vol. 34, no. 1, pp. 1–11, 2014.
  10. S. Christoph Stein, M. Schoeler, J. Papon, and F. Worgotter, “Object partitioning using local convexity,” in Proceedings of CVPR, 2014, pp. 304–311.
  11. X. Gong, M. Chen, and X. Yang, “Point cloud segmentation of 3d scattered parts sampled by realsense,” in 2017 IEEE International Conference on Information and Automation (ICIA).   IEEE, 2017, pp. 1–6.
  12. I. Armeni, A. Sax, A. R. Zamir, and S. Savarese, “Joint 2D-3D-Semantic Data for Indoor Scene Understanding,” ArXiv e-prints, Feb. 2017.
  13. V. Kreavoy, D. Julius, and A. Sheffer, “Model composition from interchangeable components,” in 15th Pacific Conference on Computer Graphics and Applications (PG’07).   IEEE, 2007, pp. 129–138.
  14. J. Lien and N. M. Amato, “Approximate convex decomposition of polyhedra,” in Proceedings of the 2007 ACM symposium on Solid and physical modeling, 2007, pp. 121–131.
  15. J. M. Lien and N. M. Amato, “Approximate convex decomposition of polyhedra and its applications,” Computer Aided Geometric Design, vol. 25, no. 7, pp. 503–522, 2008.
  16. V. K. D. J. A. Sheffer, “Shuffler: Modeling with interchangeable parts,” Visual Computer journal, 2007.
  17. H. Liu, W. Liu, and L. J. Latecki, “Convex shape decomposition,” in CVPR.   IEEE, 2010, pp. 97–104.
  18. Y. Shinagawa, T. L. Kunii, and Y. L. Kergosien, “Surface coding based on morse theory,” IEEE Computer Graphics and Applications, vol. 11, no. 05, pp. 66–78, 1991.
  19. K. Tateno, F. Tombari, and N. Navab, “Real-time and scalable incremental segmentation on dense slam,” in IROS.   IEEE, 2015, pp. 4465–4472.
  20. B. Deng, K. Genova, S. Yazdani, S. Bouaziz, G. Hinton, and A. Tagliasacchi, “Cvxnet: Learnable convex decomposition,” in CVPR, 2020, pp. 31–44.
  21. M. Gadelha, A. RoyChowdhury, G. Sharma, E. Kalogerakis, L. Cao, E. Learned-Miller, R. Wang, and S. Maji, “Label-efficient learning on point clouds using approximate convex decompositions,” in ECCV.   Springer, 2020, pp. 473–491.
  22. S. Tulsiani, H. Su, L. J. Guibas, A. A. Efros, and J. Malik, “Learning shape abstractions by assembling volumetric primitives,” in CVPR, 2017, pp. 2635–2643.
  23. C. Zou, E. Yumer, J. Yang, D. Ceylan, and D. Hoiem, “3d-prnn: Generating shape primitives with recurrent neural networks,” in ICCV, 2017, pp. 900–909.
  24. C. R. Qi, L. Yi, H. Su, and L. J. Guibas, “Pointnet++: Deep hierarchical feature learning on point sets in a metric space,” arXiv preprint arXiv:1706.02413, 2017.
  25. C. Feng, Y. Taguchi, and V. R. Kamat, “Fast plane extraction in organized point clouds using agglomerative hierarchical clustering,” in ICRA.   IEEE, 2014, pp. 6218–6225.
  26. I. Armeni, O. Sener, A. R. Zamir, H. Jiang, I. Brilakis, M. Fischer, and S. Savarese, “3d semantic parsing of large-scale indoor spaces,” in CVPR, 2016.
  27. A. Dai, A. X. Chang, M. Savva, M. Halber, T. Funkhouser, and M. Nießner, “Scannet: Richly-annotated 3d reconstructions of indoor scenes,” in Proc. CVPR, 2017.
  28. L. Yi, W. Zhao, H. Wang, M. Sung, and L. J. Guibas, “Gspn: Generative shape proposal network for 3d instance segmentation in point cloud,” in CVPR, 2019, pp. 3947–3956.
  29. Z. Liang, M. Yang, H. Li, and C. Wang, “3d instance embedding learning with a structure-aware loss function for point cloud segmentation,” IEEE Robotics and Automation Letters, vol. 5, no. 3, pp. 4915–4922, 2020.
  30. J. Chen, Z. Kira, and Y. K. Cho, “Lrgnet: Learnable region growing for class-agnostic point cloud segmentation,” IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 2799–2806, 2021.
  31. W. Wang, R. Yu, Q. Huang, and U. Neumann, “Sgpn: Similarity group proposal network for 3d point cloud instance segmentation,” in CVPR, 2018, pp. 2569–2578.
  32. L. Jiang, H. Zhao, S. Shi, S. Liu, C.-W. Fu, and J. Jia, “Pointgroup: Dual-set point grouping for 3d instance segmentation,” in CVPR, 2020, pp. 4867–4876.
  33. M. Everingham, S. A. Eslami, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman, “The pascal visual object classes challenge: A retrospective,” IJCV, vol. 111, no. 1, pp. 98–136, 2015.
  34. Q.-Y. Zhou, J. Park, and V. Koltun, “Open3D: A modern library for 3D data processing,” arXiv:1801.09847, 2018.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Slide Deck Streamline Icon: https://streamlinehq.com

Whiteboard

Dice Question Streamline Icon: https://streamlinehq.com

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. CID: Concavity-Induced Distance