Abstract
3D point cloud registration is an important task in computer vision. Due to the irregularity of point clouds, it is still a challenging problem to realize the accurate registration. Recently, with the development of deep learning, scholars have proposed many learning-based methods, which can enhance the correspondence of points and not rely on the initial alignment conditions. However, most works tend to ignore the importance of local features, leading to the unreasonable matching. To solve this issue, we propose two networks to extract richer local information. In order to find a closer internal relation between the points, a Subtract Attention Network (SANet) is designed. In which, we propose a Subtract Attention Module (SAM) to aggregate the point-wise feature representations and construct the key points of feature space on this basis. We also propose a Position Encoding Network (PENet) to determine the spatial correlation with the utility of local coordinates. After combining the spatial features of different dimensions, the connections of key points in the feature space tend to be more credible. Thus, we can effectively obtain the local correspondence between each point and then improve the accuracy of registration. The results on the commonly used dataset ModelNet40 show the superiority of our method.
Similar content being viewed by others
References
Shi J, Sun Z, Bai S (2018) 3D reconstruction framework via combining one 3D scanner and multiple stereo trackers. The Visual Computer 34(3):377–389
Han L, Xu L, Bobkov D et al (2019) Real-time global registration for globally consistent rgb-d slam. IEEE Transactions on Robotics 35(2):498–508
Deschaud JE (2018) IMLS-SLAM: scan-to-model matching based on 3D data. In: IEEE international conference on robotics and automation. pp 2480-2485
Lu W, Zhou Y, Wan G, et al (2019) L3-net: Towards learning based lidar localization for autonomous driving. In: IEEE conference on computer vision and pattern recognition. pp 6389-6398
Newell A, Yang K, Deng J (2016) Stacked hourglass networks for human pose estimation. In: European conference on computer vision. pp 483-499
Zeng A, Song S, Nießner M, et al (2017) 3dmatch: Learning local geometric descriptors from rgb-d reconstructions. In: IEEE conference on computer vision and pattern recognition. pp 1802-1811
Tombari F, Salti S, Di Stefano L (2013) Performance evaluation of 3D keypoint detectors. International Journal of Computer Vision 102(1–3):198–220
Guo Y, Bennamoun M, Sohel F et al (2016) A comprehensive performance evaluation of 3D local feature descriptors. International Journal of Computer Vision 116(1):66–89
Aiger D, Mitra N J, Cohen-Or D (2008) 4-points congruent sets for robust pairwise surface registration. In: ACM SIGGRAPH 2008 papers. pp 1-10
Drost B, Ulrich M, Navab N, et al (2010) Model globally, match locally: Efficient and robust 3D object recognition. In: IEEE computer society conference on computer vision and pattern recognition. pp 998-1005
Mellado N, Aiger D, Mitra NJ (2014) Super 4pcs fast global point cloud registration via smart indexing. Computer Graphics Forum 33(5):205–215
Papazov C, Haddadin S, Parusel S et al (2012) Rigid 3D geometry matching for grasping of known objects in cluttered scenes. The International Journal of Robotics Research 31(4):538–553
Sarode V, Li X, Goforth H, et al (2019) PCRNet: Point cloud registration network using PointNet encoding. In: IEEE international conference on computer vision
Campbell D, Petersson L (2016) Gogma: Globally-optimal gaussian mixture alignment. In: IEEE conference on computer vision and pattern recognition. pp 5685-5694
Liu Y, Wang C, Song Z, et al (2018) Efficient global point cloud registration by matching rotation invariant features through translation search. In: European conference on computer vision. pp 448-463
Enqvist O, Josephson K, Kahl F (2009) Optimal correspondences from pairwise constraints. In: IEEE 12th international conference on computer vision. pp 1295-1302
Torresani L, Kolmogorov V, Rother C (2008) Feature correspondence via graph matching: Models and global optimization. In: European conference on computer vision. pp 596-609
Wang Y, Solomon JM (2019) Prnet: Self-supervised learning for partial-to-partial registration. In: Advances in neural information processing systems. pp 8812-8824
Huang X, Mei G, Zhang J (2020) Feature-metric registration: a fast semi-supervised approach for robust point cloud registration without correspondences. In: IEEE conference on computer vision and pattern recognition. pp 11366-11374
Wang Y, Solomon JM (2019) Deep closest point: learning representations for point cloud registration. In: IEEE conference on computer vision and pattern recognition, pp 3523-3532
Yuan W, Eckart B, Kim K, et al (2020) DeepGMR: learning latent gaussian mixture models for registration. In: European conference on computer vision. pp 733-750
Fu K, Liu S, Luo X, et al (2021) Robust point cloud registration framework based on deep graph matching. In: IEEE conference on computer vision and pattern recognition. pp 8893-8902
Liu X, Zhu X, Li M et al (2019) Multiple kernel k-means with incomplete kernels. IEEE transactions on pattern analysis and machine intelligence 42(5):1191–1204
Yu X, Lu YH, Gao Q (2021) Pipeline image diagnosis algorithm based on neural immune ensemble learning. International Journal of Pressure Vessels and Piping 189:104249
Besl PJ, McKay ND (1992) Method for registration of 3-D shapes. In: International society for optics and photonics. pp 586-606
Fitzgibbon AW (2003) Robust registration of 2D and 3D point sets. Image and vision computing 21(13–14):1145–1153
Tsin Y, Kanade T (2004) A correlation-based approach to robust point set registration. In: European conference on computer vision. pp 558-569
Bouaziz S, Tagliasacchi A, Pauly M (2013) Sparse iterative closest point. Computer graphics forum 32(5):113–123
Jian B, Vemuri BC (2010) Robust point set registration using gaussian mixture models. IEEE transactions on pattern analysis and machine intelligence 33(8):1633–1645
Eckart B, Kim K, Kautz J (2018) Hgmr: Hierarchical gaussian mixtures for adaptive 3d registration. In: European conference on computer vision. pp 705-721
Yang J, Li H, Jia Y (2013) Go-icp: Solving 3d registration efficiently and globally optimally. In: IEEE international conference on computer vision. pp 1457-1464
Campbell D, Petersson L, Kneip L, et al (2019) The alignment of the spheres: Globally-optimal spherical mixture alignment for camera pose estimation. In: IEEE conference on computer vision and pattern recognition. pp 11796-11806
Qi C R, Su H, Mo K, et al (2017) Pointnet: Deep learning on point sets for 3d classification and segmentation. In: IEEE conference on computer vision and pattern recognition. pp 652-660
Aoki Y, Goforth H, Srivatsan RA, et al (2019) Pointnetlk: Robust & efficient point cloud registration using pointnet. In: IEEE conference on computer vision and pattern recognition. pp 7163-7172
Baker S, Matthews I (2004) Lucas-kanade 20 years on: A unifying framework. International journal of computer vision 56(3):221–255
Lin CH, Zhu R, Lucey S (2016) The conditional lucas & kanade algorithm. In: European conference on computer vision. pp 793-808
Vaswani A, Shazeer N, Parmar N, et al (2017) Attention is all you need. In: Advances in neural information processing systems. pp 5998-6008
Hertz A, Hanocka R, Giryes R, et al (2020) PointGMM: a neural GMM network for point clouds. In: IEEE conference on computer vision and pattern recognition. pp 12054-12063
Lu W, Wan G, Zhou Y, et al (2019) Deepvcp: An end-to-end deep neural network for point cloud registration. In: IEEE international conference on computer vision. pp 12-21
Yew ZJ, Lee GH (2020) Rpm-net: Robust point matching using learned features. In: IEEE conference on computer vision and pattern recognition. pp 11824-11833
Mafarja MM, Mirjalili S (2017) Hybrid whale optimization algorithm with simulated annealing for feature selection. Neurocomputing 260:302–312
Léger F (2021) A gradient descent perspective on Sinkhorn. Applied Mathematics & Optimization 84(2):1843–1855
Li J, Zhang C, Xu Z, et al (2019) Iterative distance-aware similarity matrix convolution with mutual-supervised point elimination for efficient point cloud registration. In: European conference on computer vision
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural networks 2(5):359–366
Lin Z, Feng M, Santos CN, et al (2017) A structured self-attentive sentence embedding. In: International conference on learning representations
Paszke A, Gross S, Massa F, et al (2019) Pytorch: An imperative style, high-performance deep learning library. In: Advances in neural information processing systems. pp 8026-8037
Wu Z, Song S, Khosla A, et al (2015) 3d shapenets: A deep representation for volumetric shapes. In: IEEE conference on computer vision and pattern recognition. pp 1912-1920
Zhou QY,Park J, Koltun V (2016) Fast global registration. In: European conference on computer vision. pp 766-782
Gold S, Rangarajan A, Lu CP et al (1998) New algorithms for 2D and 3D point matching: pose estimation and correspondence. Pattern recognition 31(8):1019–1031
Choi S, Zhou QY, Koltun V (2015) Robust reconstruction of indoor scenes. In: IEEE conference on computer vision and pattern recognition. pp 5556-5565
Acknowledgements
This work was supported by the National Natural Science Foundation of China under Grant 62171314.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, D., He, K., Wang, L. et al. Local feature extraction network with high correspondences for 3d point cloud registration. Appl Intell 52, 9638–9649 (2022). https://doi.org/10.1007/s10489-021-03055-1
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-03055-1