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

PCRDiffusion: Diffusion Probabilistic Models for Point Cloud Registration (2312.06063v1)

Published 11 Dec 2023 in cs.CV and cs.AI

Abstract: We propose a new framework that formulates point cloud registration as a denoising diffusion process from noisy transformation to object transformation. During training stage, object transformation diffuses from ground-truth transformation to random distribution, and the model learns to reverse this noising process. In sampling stage, the model refines randomly generated transformation to the output result in a progressive way. We derive the variational bound in closed form for training and provide implementations of the model. Our work provides the following crucial findings: (i) In contrast to most existing methods, our framework, Diffusion Probabilistic Models for Point Cloud Registration (PCRDiffusion) does not require repeatedly update source point cloud to refine the predicted transformation. (ii) Point cloud registration, one of the representative discriminative tasks, can be solved by a generative way and the unified probabilistic formulation. Finally, we discuss and provide an outlook on the application of diffusion model in different scenarios for point cloud registration. Experimental results demonstrate that our model achieves competitive performance in point cloud registration. In correspondence-free and correspondence-based scenarios, PCRDifussion can both achieve exceeding 50\% performance improvements.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (71)
  1. H. Guo, J. Zhu, and Y. Chen, “E-loam: Lidar odometry and mapping with expanded local structural information,” IEEE Transactions on Intelligent Vehicles, vol. 8, no. 2, pp. 1911–1921, 2023.
  2. J. Engel, J. Stückler, and D. Cremers, “Large-scale direct slam with stereo cameras,” in IEEE/RSJ International Conference on Intelligent Robots and Systems, 2015, pp. 1935–1942.
  3. H. Guo, S. Peng, H. Lin, Q. Wang, G. Zhang, H. Bao, and X. Zhou, “Neural 3d scene reconstruction with the manhattan-world assumption,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5511–5520.
  4. Y. Siddiqui, J. Thies, F. Ma, Q. Shan, M. Nießner, and A. Dai, “Retrievalfuse: Neural 3d scene reconstruction with a database,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 12 568–12 577.
  5. J. Sun, Z. Wang, S. Zhang, X. He, H. Zhao, G. Zhang, and X. Zhou, “Onepose: One-shot object pose estimation without cad models,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 6825–6834.
  6. T. Lee, B.-U. Lee, I. Shin, J. Choe, U. Shin, I. S. Kweon, and K.-J. Yoon, “Uda-cope: unsupervised domain adaptation for category-level object pose estimation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 14 891–14 900.
  7. Z. Zhu, S. Peng, V. Larsson, W. Xu, H. Bao, Z. Cui, M. R. Oswald, and M. Pollefeys, “Nice-slam: Neural implicit scalable encoding for slam,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 12 786–12 796.
  8. Y. Fan, Q. Zhang, Y. Tang, S. Liu, and H. Han, “Blitz-slam: A semantic slam in dynamic environments,” Pattern Recognition, vol. 121, p. 108225, 2022.
  9. Y. Aoki, H. Goforth, R. A. Srivatsan, and S. Lucey, “Pointnetlk: Robust & efficient point cloud registration using pointnet,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 7163–7172.
  10. 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.
  11. G. Mei, “Point cloud registration with self-supervised feature learning and beam search,” in Digital Image Computing: Techniques and Applications.   IEEE, 2021, pp. 01–08.
  12. G. Mei, X. Huang, J. Zhang, and Q. Wu, “Partial point cloud registration via soft segmentation,” in IEEE International Conference on Image Processing.   IEEE, 2022, pp. 681–685.
  13. H. Xu, S. Liu, G. Wang, G. Liu, and B. Zeng, “Omnet: Learning overlapping mask for partial-to-partial point cloud registration,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 3132–3141.
  14. 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.
  15. 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.
  16. 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.
  17. 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.
  18. J. Ho, A. Jain, and P. Abbeel, “Denoising diffusion probabilistic models,” Advances in Neural Information Processing Systems, vol. 33, pp. 6840–6851, 2020.
  19. J. Austin, D. D. Johnson, J. Ho, D. Tarlow, and R. van den Berg, “Structured denoising diffusion models in discrete state-spaces,” Advances in Neural Information Processing Systems, vol. 34, pp. 17 981–17 993, 2021.
  20. O. Avrahami, D. Lischinski, and O. Fried, “Blended diffusion for text-driven editing of natural images,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 18 208–18 218.
  21. L. Zhou, Y. Du, and J. Wu, “3d shape generation and completion through point-voxel diffusion,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 5826–5835.
  22. Z. Lyu, Z. Kong, X. Xu, L. Pan, and D. Lin, “A conditional point diffusion-refinement paradigm for 3d point cloud completion,” arXiv preprint arXiv:2112.03530, 2021.
  23. T. Amit, T. Shaharbany, E. Nachmani, and L. Wolf, “Segdiff: Image segmentation with diffusion probabilistic models,” arXiv preprint arXiv:2112.00390, 2021.
  24. D. Baranchuk, I. Rubachev, A. Voynov, V. Khrulkov, and A. Babenko, “Label-efficient semantic segmentation with diffusion models,” arXiv preprint arXiv:2112.03126, 2021.
  25. E. A. Brempong, S. Kornblith, T. Chen, N. Parmar, M. Minderer, and M. Norouzi, “Denoising pretraining for semantic segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4175–4186.
  26. T. Chen, L. Li, S. Saxena, G. Hinton, and D. J. Fleet, “A generalist framework for panoptic segmentation of images and videos,” arXiv preprint arXiv:2210.06366, 2022.
  27. A. Graikos, N. Malkin, N. Jojic, and D. Samaras, “Diffusion models as plug-and-play priors,” arXiv preprint arXiv:2206.09012, 2022.
  28. B. Kim, Y. Oh, and J. C. Ye, “Diffusion adversarial representation learning for self-supervised vessel segmentation,” arXiv preprint arXiv:2209.14566, 2022.
  29. J. Wolleb, R. Sandkühler, F. Bieder, P. Valmaggia, and P. C. Cattin, “Diffusion models for implicit image segmentation ensembles,” in International Conference on Medical Imaging with Deep Learning.   PMLR, 2022, pp. 1336–1348.
  30. J. Sohl-Dickstein, E. Weiss, N. Maheswaranathan, and S. Ganguli, “Deep unsupervised learning using nonequilibrium thermodynamics,” in International Conference on Machine Learning.   PMLR, 2015, pp. 2256–2265.
  31. C. R. Qi, H. Su, K. Mo, and L. J. Guibas, “Pointnet: Deep learning on point sets for 3d classification and segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2017, pp. 652–660.
  32. Y. Wang, Y. Sun, Z. Liu, S. E. Sarma, M. M. Bronstein, and J. M. Solomon, “Dynamic graph cnn for learning on point clouds,” ACM Transactions On Graphics, vol. 38, no. 5, pp. 1–12, 2019.
  33. C. R. Qi, L. Yi, H. Su, and L. J. Guibas, “Pointnet++: Deep hierarchical feature learning on point sets in a metric space,” Advances in Neural Information Processing Systems, vol. 30, 2017.
  34. Z. Wu, S. Song, A. Khosla, F. Yu, L. Zhang, X. Tang, and J. Xiao, “3d shapenets: A deep representation for volumetric shapes,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2015, pp. 1912–1920.
  35. 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/CVF Conference on Computer Vision and Pattern Recognition, 2017, pp. 1802–1811.
  36. A. Geiger, P. Lenz, and R. Urtasun, “Are we ready for autonomous driving? the kitti vision benchmark suite,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012, pp. 3354–3361.
  37. P. J. Besl and N. D. McKay, “Method for registration of 3-d shapes,” in Sensor fusion IV: Control Paradigms and Data Structures, 1992, pp. 586–606.
  38. A. Kurobe, Y. Sekikawa, K. Ishikawa, and H. Saito, “Corsnet: 3d point cloud registration by deep neural network,” IEEE Robotics and Automation Letters, vol. 5, no. 3, pp. 3960–3966, 2020.
  39. A. Segal, D. Haehnel, and S. Thrun, “Generalized-icp.” in Robotics: Science and Systems, 2009.
  40. J. Yang, H. Li, D. Campbell, and Y. Jia, “Go-icp: A globally optimal solution to 3d icp point-set registration,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 11, pp. 2241–2254, 2015.
  41. S. Bouaziz, A. Tagliasacchi, and M. Pauly, “Sparse iterative closest point,” in Computer Graphics Forum, 2013, pp. 113–123.
  42. A. W. Fitzgibbon, “Robust registration of 2d and 3d point sets,” Image and Vision Computing, vol. 21, no. 13-14, pp. 1145–1153, 2003.
  43. S. Rusinkiewicz, “A symmetric objective function for icp,” ACM Transactions on Graphics, vol. 38, no. 4, pp. 1–7, 2019.
  44. B. Bellekens, V. Spruyt, R. Berkvens, R. Penne, and M. Weyn, “A benchmark survey of rigid 3d point cloud registration algorithms,” in Proceedings of International Conference on Ambient Computing, Applications, Services and Technologies, 2015, pp. 118–127.
  45. S. Du, G. Xu, S. Zhang, X. Zhang, Y. Gao, and B. Chen, “Robust rigid registration algorithm based on pointwise correspondence and correntropy,” Pattern Recognition Letters, vol. 132, pp. 91–98, 2020.
  46. D. Chetverikov, D. Svirko, D. Stepanov, and P. Krsek, “The trimmed iterative closest point algorithm,” in International Conference on Pattern Recognition, vol. 3, 2002, pp. 545–548.
  47. S. Rusinkiewicz and M. Levoy, “Efficient variants of the icp algorithm,” in Proceedings of International Conference on 3-D Digital Imaging and Modeling, 2001, pp. 145–152.
  48. V. Sarode, X. Li, H. Goforth, Y. Aoki, R. A. Srivatsan, S. Lucey, and H. Choset, “Pcrnet: Point cloud registration network using pointnet encoding,” arXiv preprint arXiv:1908.07906, 2019.
  49. J. Li, C. Zhang, Z. Xu, H. Zhou, and C. Zhang, “Iterative distance-aware similarity matrix convolution with mutual-supervised point elimination for efficient point cloud registration,” in European Conference on Computer Vision, 2020, pp. 378–394.
  50. Y. Yuan, Y. Wu, X. Fan, M. Gong, W. Ma, and Q. Miao, “Egst: Enhanced geometric structure transformer for point cloud registration,” IEEE Transactions on Visualization & Computer Graphics, no. 01, pp. 1–13, 2023.
  51. Z. Dang, F. Wang, and M. Salzmann, “Learning 3d-3d correspondences for one-shot partial-to-partial registration,” arXiv preprint arXiv:2006.04523, 2020.
  52. M. Cuturi, “Sinkhorn distances: Lightspeed computation of optimal transport,” Advances in Neural Information Processing Systems, vol. 26, 2013.
  53. Z. J. Yew and G. H. Lee, “Rpm-net: Robust point matching using learned features,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11 824–11 833.
  54. H. Deng, T. Birdal, and S. Ilic, “Ppfnet: Global context aware local features for robust 3d point matching,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 195–205.
  55. Y. Song and S. Ermon, “Generative modeling by estimating gradients of the data distribution,” Advances in Neural Information Processing Systems, vol. 32, 2019.
  56. Y. Song, J. Sohl-Dickstein, D. P. Kingma, A. Kumar, S. Ermon, and B. Poole, “Score-based generative modeling through stochastic differential equations,” arXiv preprint arXiv:2011.13456, 2020.
  57. I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial networks,” Communications of the ACM, vol. 63, no. 11, pp. 139–144, 2020.
  58. P. Dhariwal and A. Nichol, “Diffusion models beat gans on image synthesis,” Advances in Neural Information Processing Systems, vol. 34, pp. 8780–8794, 2021.
  59. E. Mathieu and M. Nickel, “Riemannian continuous normalizing flows,” Advances in Neural Information Processing Systems, vol. 33, pp. 2503–2515, 2020.
  60. S. Luo and W. Hu, “Diffusion probabilistic models for 3d point cloud generation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 2837–2845.
  61. ——, “Score-based point cloud denoising,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 4583–4592.
  62. A. Vahdat, F. Williams, Z. Gojcic, O. Litany, S. Fidler, K. Kreis et al., “Lion: Latent point diffusion models for 3d shape generation,” Advances in Neural Information Processing Systems, vol. 35, pp. 10 021–10 039, 2022.
  63. S. Chen, P. Sun, Y. Song, and P. Luo, “Diffusiondet: Diffusion model for object detection,” arXiv preprint arXiv:2211.09788, 2022.
  64. D. P. Kingma and M. Welling, “Auto-encoding variational bayes,” arXiv preprint arXiv:1312.6114, 2013.
  65. A. Q. Nichol and P. Dhariwal, “Improved denoising diffusion probabilistic models,” in International Conference on Machine Learning.   PMLR, 2021, pp. 8162–8171.
  66. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back-propagating errors,” nature, vol. 323, no. 6088, pp. 533–536, 1986.
  67. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
  68. Q.-Y. Zhou, J. Park, and V. Koltun, “Fast global registration,” in European Conference on Computer Vision, 2016, pp. 766–782.
  69. W. Yuan, B. Eckart, K. Kim, V. Jampani, D. Fox, and J. Kautz, “Deepgmr: Learning latent gaussian mixture models for registration,” in European Conference on Computer Vision, 2020, pp. 733–750.
  70. Y. Wang and J. M. Solomon, “Deep closest point: Learning representations for point cloud registration,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 3523–3532.
  71. Q.-Y. Zhou, J. Park, and V. Koltun, “Open3d: A modern library for 3d data processing,” arXiv preprint arXiv:1801.09847, 2018.
Citations (1)
View on Semantic Scholar

Summary

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

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