POE-Net: EXPAND-LAPLACIAN ATTENTION NETWORK FOR LARGE-SCALE PLACE RECOGNITION IN POINT CLOUD

Kunfei Li, Youqiang Dong, Bongrae Park, Thomas Koch, and Zhibo Wan

References

  1. [1] Y. Fu, Q. Yan, L. Yang, J. Liao, and C. Xiao, Texturemapping for 3D reconstruction with RGB-D sensor, Proceedingof the IEEE Conference on Computer Vision and PatternRecognition, Salt Lake City, UT, 2018, 4645–4653.
  2. [2] R. Mur-Artal, J. M. M. Montiel, and J. D. Tard´os, ORB-SLAM: A versatile and accurate monocular SLAM system,IEEE Transactions on Robotics, 31(5), 1147–1163, 2015.
  3. [3] C. H¨ane, L. Heng, G.H. Lee, F. Fraundorfer, P. Furgale,T. Sattler, and M. Pollefeys, 3D visual perception forself-driving cars using a multi-camera system: Calibration,mapping, localization, and obstacle detection, Image and VisionComputing, 68, 1427, 2017.
  4. [4] G.H. Lee, F. Faundorfer, and M. Pollefeys, Motion estimationfor self-driving cars with a generalized camera, Proceedingof the IEEE Conference on Computer Vision and PatternRecognition, Portland, OR, 2013, 2746–2753.
  5. [5] Y. Li, N. Snavely, and D.P. Huttenlocher, Location recognitionusing prioritized feature matching, Proceeding 11th EuropeanConference on Computer Vision (ECCV), Heraklion, Greece,2010, 791–804.
  6. [6] L. Liu, H. Li, and Y. Dai, Efficient global 2D-3D matching forcamera localization in a large-scale 3D map, Proceeding of theIEEE International Conference on Computer Vision, Venice,Italy, 2017, 2372–2381.
  7. [7] L. Liu, H. Li, and Y. Dai, Stochastic attraction-repulsionembedding for large scale image localization, Proceedings ofthe IEEE/CVF International Conference on Computer Vision,2019, 2570–2579.
  8. [8] M.A. Uy and G.H. Lee, PointNetVLAD: Deep point cloudbased retrieval for large-scale place recognition, Proceedingsof the IEEE Conference on Computer Vision and PatternRecognition, 2018, 4470–4479.
  9. [9] R.Q. Charles, H. Su, M. Kaichun, and L.J. Guibas,Pointnet: Deep learning on point sets for 3D classifica-tion and segmentation, Proceedings of the IEEE Confer-ence on Computer Vision and Pattern Recognition, 2017,652–660.
  10. [10] R. Arandjelovic, P. Gronat, A. Torii, T. Pajdla, and J. Sivic,NetVLAD: CNN architecture for weakly supervised placerecognition, Proceedings of the IEEE Conference on ComputerVision and Pattern Recognition, 2016, 5297–5307.
  11. [11] W. Zhang and C. Xiao, PCAN: 3D attention map learningusing contextual information for point cloud based retrieval,Proceedings of the IEEE/CVF Conference on Computer Visionand Pattern Recognition, 2019, 12436–12445.
  12. [12] C.R. Qi, L. Yi, H. Su, and L.J. Guibas, Pointnet++:Deep hierarchical feature learning on point sets in ametric space, Proceedings of the 31st International Con-ference on Neural Information Processing Systems, 2017,5105–5114.
  13. [13] A.E. Johnson and M. Hebert, Using spin images for efficientobject recognition in cluttered 3D scenes, IEEE Transactionson Pattern Analysis and Machine Intelligence, 21(5), 1999,433–449.
  14. [14] A. Frome, D. Huber, R. Kolluri, T. B¨ulow, and J.Malik, Recognizing objects in range data using regionalpoint descriptors, Proceedings 8th European Conferenceon Computer Vision (ECCV), Berlin, Germany, 2004,224–237.
  15. [15] J. Du, R. Wang, and D. Cremers, DH3D: Deep hierarchical3D descriptors for robust large-scale 6DoF relocalization,Proceedings 16th European Conference Computer Vision(ECCV), Glasgow, U.K., 2020, 744–762.
  16. [16] Q. Sun, H. Liu, J. He, Z. Fan, and X. Du,, DAGC: Employingdual attention and graph convolution for point cloud basedplace recognition, Proceedings of the International Conferenceon Multimedia Retrieval, 2020, 224–232.7
  17. [17] M.-H. Guo, J.-X. Cai, Z.-N. Liu, T.-J. Mu, R.-R. Martin,and S.-M. Hu, ”PCT: Point cloud transformer, ComputationalVisual Media, 7, 2021, 187–199.
  18. [18] M.-H. Guo, Z.-N. Liu, T.-J. Mu, and S.-M. Hu, Beyond self-attention: External attention using two linear layers for visualtasks, IEEE Transactions on Pattern Analysis and MachineIntelligence, 45(5), 2022, 5436–5447.
  19. [19] H. Zhao, L. Jiang, J. Jia, P. Torr, and V. Koltun, Pointtransformer, Proceedings of the IEEE/CVF InternationalConference on Computer Vision, 2021, 16259–16268.
  20. [20] J. Bruna, W. Zaremba, A. Szlam, and Y. LeCun, Spectralnetworks and locally connected networks on graphs, 2013,arXiv:1312.6203.
  21. [21] K. Han, Y. Wang, H. Chen, X. Chen, J. Guo, Z. Liu, Y.Tang, A. Xiao, C. Xu, Y. Xu, and Z. Yang, A survey onvision transformer, IEEE Transactions on Pattern Analysisand Machine Intelligence, 45(1), 2022, 87–110.
  22. [22] J. Komorowski, MinkLoc3D: Point cloud based large-scale placerecognition, Proceedings of the IEEE/CVF Winter Conferenceon Applications of Computer Vision, 2021, 1790–1799.
  23. [23] W. Maddern, G. Pascoe, C. Linegar, and P. Newman, 1 year,1000 km: The oxford robotcar dataset, The InternationalJournal of Robotics Research, 36(1), 2017, 3–15.

Important Links:

Go Back