Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

SGNet: Salient Geometric Network for Point Cloud Registration (2309.06207v5)

Published 12 Sep 2023 in cs.CV

Abstract: Point Cloud Registration (PCR) is a critical and challenging task in computer vision. One of the primary difficulties in PCR is identifying salient and meaningful points that exhibit consistent semantic and geometric properties across different scans. Previous methods have encountered challenges with ambiguous matching due to the similarity among patch blocks throughout the entire point cloud and the lack of consideration for efficient global geometric consistency. To address these issues, we propose a new framework that includes several novel techniques. Firstly, we introduce a semantic-aware geometric encoder that combines object-level and patch-level semantic information. This encoder significantly improves registration recall by reducing ambiguity in patch-level superpoint matching. Additionally, we incorporate a prior knowledge approach that utilizes an intrinsic shape signature to identify salient points. This enables us to extract the most salient super points and meaningful dense points in the scene. Secondly, we introduce an innovative transformer that encodes High-Order (HO) geometric features. These features are crucial for identifying salient points within initial overlap regions while considering global high-order geometric consistency. To optimize this high-order transformer further, we introduce an anchor node selection strategy. By encoding inter-frame triangle or polyhedron consistency features based on these anchor nodes, we can effectively learn high-order geometric features of salient super points. These high-order features are then propagated to dense points and utilized by a Sinkhorn matching module to identify key correspondences for successful registration. In our experiments conducted on well-known datasets such as 3DMatch/3DLoMatch and KITTI, our approach has shown promising results, highlighting the effectiveness of our novel method.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. Z. Qin, H. Yu, C. Wang, Y. Guo, Y. Peng, and K. Xu, “Geometric transformer for fast and robust point cloud registration,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11 143–11 152.
  2. X. Huang, G. Mei, J. Zhang, and R. Abbas, “A comprehensive survey on point cloud registration,” 2021.
  3. C. Cadena, L. Carlone, H. Carrillo, Y. Latif, D. Scaramuzza, J. Neira, I. Reid, and J. J. Leonard, “Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age,” IEEE Transactions on robotics, vol. 32, no. 6, pp. 1309–1332, 2016.
  4. J. L. Schonberger and J.-M. Frahm, “Structure-from-motion revisited,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 4104–4113.
  5. S. Choi, Q.-Y. Zhou, and V. Koltun, “Robust reconstruction of indoor scenes,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 5556–5565.
  6. J. Zhang and S. Singh, “Visual-lidar odometry and mapping: Low-drift, robust, and fast,” in 2015 IEEE International Conference on Robotics and Automation (ICRA).   IEEE, 2015, pp. 2174–2181.
  7. H. Thomas, C. R. Qi, J.-E. Deschaud, B. Marcotegui, F. Goulette, and L. J. Guibas, “Kpconv: Flexible and deformable convolution for point clouds,” in Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 6411–6420.
  8. X. Bai, Z. Luo, L. Zhou, H. Fu, L. Quan, and C.-L. Tai, “D3feat: Joint learning of dense detection and description of 3d local features,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 6359–6367.
  9. S. Huang, Z. Gojcic, M. Usvyatsov, A. Wieser, and K. Schindler, “Predator: Registration of 3d point clouds with low overlap,” in Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition, 2021, pp. 4267–4276.
  10. H. Yu, F. Li, M. Saleh, B. Busam, and S. Ilic, “Cofinet: Reliable coarse-to-fine correspondences for robust pointcloud registration,” Advances in Neural Information Processing Systems, vol. 34, pp. 23 872–23 884, 2021.
  11. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” Advances in neural information processing systems, vol. 30, 2017.
  12. Z. Qin, H. Yu, C. Wang, Y. Guo, Y. Peng, S. Ilic, D. Hu, and K. Xu, “Geotransformer: Fast and robust point cloud registration with geometric transformer,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 8, pp. 9806–9821, 2023.
  13. X. Bai, Z. Luo, L. Zhou, H. Chen, L. Li, Z. Hu, H. Fu, and C.-L. Tai, “Pointdsc: Robust point cloud registration using deep spatial consistency,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 15 859–15 869.
  14. R. Wang, J. Yan, and X. Yang, “Neural graph matching network: Learning lawler’s quadratic assignment problem with extension to hypergraph and multiple-graph matching,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 9, pp. 5261–5279, 2021.
  15. J. Lee, M. Cho, and K. M. Lee, “Hyper-graph matching via reweighted random walks,” in CVPR 2011.   IEEE, 2011, pp. 1633–1640.
  16. Y. Zhong, “Intrinsic shape signatures: A shape descriptor for 3d object recognition,” in 2009 IEEE 12th international conference on computer vision workshops, ICCV workshops.   IEEE, 2009, pp. 689–696.
  17. Z. Chen, H. Chen, L. Gong, X. Yan, J. Wang, Y. Guo, J. Qin, and M. Wei, “Utopic: Uncertainty-aware overlap prediction network for partial point cloud registration,” arXiv preprint arXiv:2208.02712, 2022.
  18. M. Dusmanu, I. Rocco, T. Pajdla, M. Pollefeys, J. Sivic, A. Torii, and T. Sattler, “D2-net: A trainable cnn for joint description and detection of local features,” in Proceedings of the ieee/cvf conference on computer vision and pattern recognition, 2019, pp. 8092–8101.
  19. S. Ao, Q. Hu, B. Yang, A. Markham, and Y. Guo, “Spinnet: Learning a general surface descriptor for 3d point cloud registration,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 11 753–11 762.
  20. A. Zeng, S. Song, M. Nießner, M. Fisher, J. Xiao, and T. Funkhouser, “3dmatch: Learning local geometric descriptors from rgb-d reconstructions,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 1802–1811.
  21. A. Geiger, P. Lenz, C. Stiller, and R. Urtasun, “Vision meets robotics: The kitti dataset,” The International Journal of Robotics Research, vol. 32, no. 11, pp. 1231–1237, 2013.
  22. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga et al., “Pytorch: An imperative style, high-performance deep learning library,” Advances in neural information processing systems, vol. 32, 2019.
  23. I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” arXiv preprint arXiv:1711.05101, 2017.
  24. C. Choy, J. Park, and V. Koltun, “Fully convolutional geometric features,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 8958–8966.
  25. H. Yu, J. Hou, Z. Qin, M. Saleh, I. Shugurov, K. Wang, B. Busam, and S. Ilic, “Riga: Rotation-invariant and globally-aware descriptors for point cloud registration,” arXiv preprint arXiv:2209.13252, 2022.
  26. Z. J. Yew and G. H. Lee, “Regtr: End-to-end point cloud correspondences with transformers,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 6677–6686.
  27. Y. Li and T. Harada, “Lepard: Learning partial point cloud matching in rigid and deformable scenes,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5554–5564.
  28. H. Yu, Z. Qin, J. Hou, M. Saleh, D. Li, B. Busam, and S. Ilic, “Rotation-invariant transformer for point cloud matching,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 5384–5393.
  29. J. Gao, Q. Dong, R. Wang, S. Chen, S. Xin, C. Tu, and W. Wang, “Oaaformer: Robust and efficient point cloud registration through overlapping-aware attention in transformer,” arXiv preprint arXiv:2310.09817, 2023.
  30. Z. Chen, K. Sun, F. Yang, and W. Tao, “Sc2-pcr: A second order spatial compatibility for efficient and robust point cloud registration,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 13 221–13 231.
  31. J. Yu, L. Ren, Y. Zhang, W. Zhou, L. Lin, and G. Dai, “Peal: Prior-embedded explicit attention learning for low-overlap point cloud registration,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 17 702–17 711.
  32. X. Huang, G. Mei, and J. Zhang, “Feature-metric registration: A fast semi-supervised approach for robust point cloud registration without correspondences,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 11 366–11 374.
  33. C. Choy, W. Dong, and V. Koltun, “Deep global registration,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 2514–2523.
  34. F. Lu, G. Chen, Y. Liu, L. Zhang, S. Qu, S. Liu, and R. Gu, “Hregnet: A hierarchical network for large-scale outdoor lidar point cloud registration,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 16 014–16 023.
  35. P. J. Besl and N. D. McKay, “Method for registration of 3-d shapes,” in Sensor fusion IV: control paradigms and data structures, vol. 1611.   Spie, 1992, pp. 586–606.

Summary

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

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