Papers
Topics
Authors
Recent
Search
2000 character limit reached

DIPR: Efficient Point Cloud Registration via Dynamic Iteration

Published 5 Dec 2023 in cs.CV | (2312.02877v2)

Abstract: Point cloud registration (PCR) is an essential task in 3D vision. Existing methods achieve increasingly higher accuracy. However, a large proportion of non-overlapping points in point cloud registration consume a lot of computational resources while negatively affecting registration accuracy. To overcome this challenge, we introduce a novel Efficient Point Cloud Registration via Dynamic Iteration framework, DIPR, that makes the neural network interactively focus on overlapping points based on sparser input points. We design global and local registration stages to achieve efficient course-tofine processing. Beyond basic matching modules, we propose the Refined Nodes to narrow down the scope of overlapping points by using adopted density-based clustering to significantly reduce the computation amount. And our SC Classifier serves as an early-exit mechanism to terminate the registration process in time according to matching accuracy. Extensive experiments on multiple datasets show that our proposed approach achieves superior registration accuracy while significantly reducing computational time and GPU memory consumption compared to state-of-the-art methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (68)
  1. Spinnet: Learning a general surface descriptor for 3d point cloud registration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11753–11762, 2021.
  2. Buffer: Balancing accuracy, efficiency, and generalizability in point cloud registration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1255–1264, 2023.
  3. Pointnetlk: Robust & efficient point cloud registration using pointnet. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 7163–7172, 2019.
  4. Pointdsc: Robust point cloud registration using deep spatial consistency. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15859–15869, 2021.
  5. Graph-cut ransac. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 6733–6741, 2018.
  6. Seernet: Predicting convolutional neural network feature-map sparsity through low-bit quantization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11216–11225, 2019.
  7. Dynamic region-aware convolution. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8064–8073, 2021.
  8. Utopic: Uncertainty-aware overlap prediction network for partial point cloud registration. In Computer Graphics Forum, pages 87–98. Wiley Online Library, 2022a.
  9. 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, pages 13221–13231, 2022b.
  10. Sc22{}^{2}start_FLOATSUPERSCRIPT 2 end_FLOATSUPERSCRIPT-pcr++: Rethinking the generation and selection for efficient and robust point cloud registration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
  11. Fully convolutional geometric features. In Proceedings of the IEEE/CVF international conference on computer vision, pages 8958–8966, 2019.
  12. Deep global registration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2514–2523, 2020.
  13. Multi-view point clouds registration and stitching based on sift feature. In 2011 3rd International Conference on Computer Research and Development, pages 274–278. IEEE, 2011.
  14. Ppfnet: Global context aware local features for robust 3d point matching. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 195–205, 2018.
  15. 3d local features for direct pairwise registration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 3244–3253, 2019.
  16. More is less: A more complicated network with less inference complexity. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5840–5848, 2017.
  17. A density-based algorithm for discovering clusters in large spatial databases with noise. In kdd, pages 226–231, 1996.
  18. Watching a small portion could be as good as watching all: Towards efficient video classification. In IJCAI International Joint Conference on Artificial Intelligence, 2018.
  19. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6):381–395, 1981.
  20. Evsac: accelerating hypotheses generation by modeling matching scores with extreme value theory. In Proceedings of the IEEE international conference on computer vision, pages 2472–2479, 2013.
  21. Are we ready for autonomous driving? the kitti vision benchmark suite. In 2012 IEEE conference on computer vision and pattern recognition, pages 3354–3361. IEEE, 2012.
  22. Frameexit: Conditional early exiting for efficient video recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15608–15618, 2021.
  23. Dynamic neural networks: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(11):7436–7456, 2021.
  24. Learning to weight samples for dynamic early-exiting networks. In European Conference on Computer Vision, pages 362–378. Springer, 2022.
  25. Channel selection using gumbel softmax. In European Conference on Computer Vision, pages 241–257. Springer, 2020.
  26. Dynamic adaptive point cloud streaming. In Proceedings of the 23rd Packet Video Workshop, pages 25–30, 2018.
  27. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017.
  28. Meta-sr: A magnification-arbitrary network for super-resolution. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1575–1584, 2019.
  29. Multi-scale dense networks for resource efficient image classification. ICLR 2018, 2018.
  30. Predator: Registration of 3d point clouds with low overlap-supplementary material.
  31. Planning with learned dynamic model for unsupervised point cloud registration. arXiv preprint arXiv:2108.02613, 2021.
  32. Semantic mapping for mobile robotics tasks: A survey. Robotics and Autonomous Systems, 66:86–103, 2015.
  33. A sparse texture representation using local affine regions. IEEE transactions on pattern analysis and machine intelligence, 27(8):1265–1278, 2005.
  34. Improved techniques for training adaptive deep networks. In Proceedings of the IEEE/CVF international conference on computer vision, pages 1891–1900, 2019.
  35. Adavit: Adaptive vision transformers for efficient image recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12309–12318, 2022.
  36. Adafuse: Adaptive temporal fusion network for efficient action recognition. In International Conference on Learning Representations, 2020.
  37. 3dregnet: A deep neural network for 3d point registration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 7193–7203, 2020.
  38. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 652–660, 2017.
  39. Geometric transformer for fast and robust point cloud registration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11143–11152, 2022.
  40. Sbnet: Sparse blocks network for fast inference. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 8711–8720, 2018.
  41. Fast geometric point labeling using conditional random fields. In 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 7–12. IEEE, 2009.
  42. Shot: Unique signatures of histograms for surface and texture description. Computer Vision and Image Understanding, 125:251–264, 2014.
  43. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4510–4520, 2018.
  44. Superglue: Learning feature matching with graph neural networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4938–4947, 2020.
  45. Pcrnet: Point cloud registration network using pointnet encoding. arXiv preprint arXiv:1908.07906, 2019.
  46. Dynamic network quantization for efficient video inference. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 7375–7385, 2021.
  47. Learning parallel dense correspondence from spatio-temporal descriptors for efficient and robust 4d reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6022–6031, 2021.
  48. Kpconv: Flexible and deformable convolution for point clouds. In Proceedings of the IEEE/CVF international conference on computer vision, pages 6411–6420, 2019.
  49. Convolutional networks with adaptive inference graphs. In Proceedings of the European Conference on Computer Vision (ECCV), pages 3–18, 2018.
  50. Dynamic convolutions: Exploiting spatial sparsity for faster inference. In Proceedings of the ieee/cvf conference on computer vision and pattern recognition, pages 2320–2329, 2020.
  51. You only hypothesize once: Point cloud registration with rotation-equivariant descriptors. In Proceedings of the 30th ACM International Conference on Multimedia, pages 1630–1641, 2022a.
  52. Glance and focus: a dynamic approach to reducing spatial redundancy in image classification. Advances in Neural Information Processing Systems, 33:2432–2444, 2020.
  53. Adafocus v2: End-to-end training of spatial dynamic networks for video recognition. In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 20030–20040. IEEE, 2022b.
  54. Condconv: Conditionally parameterized convolutions for efficient inference. Advances in neural information processing systems, 32, 2019.
  55. One-inlier is first: Towards efficient position encoding for point cloud registration. Advances in Neural Information Processing Systems, 35:6982–6995, 2022.
  56. Teaser: Fast and certifiable point cloud registration. IEEE Transactions on Robotics, 37(2):314–333, 2020.
  57. End-to-end learning of action detection from frame glimpses in videos. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2678–2687, 2016.
  58. Rpm-net: Robust point matching using learned features. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11824–11833, 2020.
  59. Regtr: End-to-end point cloud correspondences with transformers. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 6677–6686, 2022.
  60. Cofinet: Reliable coarse-to-fine correspondences for robust pointcloud registration. Advances in Neural Information Processing Systems, 34:23872–23884, 2021.
  61. Riga: Rotation-invariant and globally-aware descriptors for point cloud registration. arXiv preprint arXiv:2209.13252, 2022.
  62. Boosted dynamic neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 10989–10997, 2023a.
  63. Rotation-invariant transformer for point cloud matching. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5384–5393, 2023b.
  64. A survey of autonomous driving: Common practices and emerging technologies. IEEE access, 8:58443–58469, 2020.
  65. 3dmatch: Learning local geometric descriptors from rgb-d reconstructions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1802–1811, 2017.
  66. 3d registration with maximal cliques. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 17745–17754, 2023.
  67. Pcr-cg: Point cloud registration via deep explicit color and geometry. In European Conference on Computer Vision, pages 443–459. Springer, 2022.
  68. Learning deep features for discriminative localization. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2921–2929, 2016.
Citations (1)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

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

Continue Learning

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

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

Authors (4)

  1. Yang Ai 
  2. Qiang Bai 
  3. Jindong Li 
  4. Xi Yang 

Collections

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

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