publication . Preprint . 2020

Self-supervised Point Set Local Descriptors for Point Cloud Registration

Yuan, Yijun; Hou, Jiawei; Nüchter, Andreas; Schwertfeger, Sören;
Open Access English
  • Published: 11 Mar 2020
Abstract
In this work, we propose to learn local descriptors for point clouds in a self-supervised manner. In each iteration of the training, the input of the network is merely one unlabeled point cloud. On top of our previous work, that directly solves the transformation between two point sets in one step without correspondences, the proposed method is able to train from one point cloud, by supervising its self-rotation, that we randomly generate. The whole training requires no manual annotation. In several experiments we evaluate the performance of our method on various datasets and compare to other state of the art algorithms. The results show, that our self-supervise...
Subjects
arXiv: Computer Science::Machine Learning
ACM Computing Classification System: ComputingMethodologies_PATTERNRECOGNITION
free text keywords: Computer Science - Robotics
Related Organizations
Download from
31 references, page 1 of 3

[1] H. Durrant-Whyte and T. Bailey, “Simultaneous localization and mapping: part i,” IEEE robotics & automation magazine, vol. 13, no. 2, pp. 99-110, 2006.

[2] Y. Zhong, “A shape descriptor for 3d object recognition,” in Proceedings ICCV 2009 Workshop 3DRR, vol. 6, 2009.

[3] R. B. Rusu, N. Blodow, and M. Beetz, “Fast point feature histograms (fpfh) for 3d registration,” in 2009 IEEE international conference on robotics and automation. IEEE, 2009, pp. 3212-3217.

[4] 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.

[5] Z. Gojcic, C. Zhou, J. D. Wegner, and A. Wieser, “The perfect match: 3d point cloud matching with smoothed densities,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 5545-5554. [OpenAIRE]

[6] 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.

[7] Z. J. Yew and G. H. Lee, “3dfeat-net: Weakly supervised local 3d features for point cloud registration,” in European Conference on Computer Vision. Springer, 2018, pp. 630-646.

[8] A. Dosovitskiy, P. Fischer, J. T. Springenberg, M. Riedmiller, and T. Brox, “Discriminative unsupervised feature learning with exemplar convolutional neural networks,” IEEE transactions on pattern analysis and machine intelligence, vol. 38, no. 9, pp. 1734-1747, 2015.

[9] S. Gidaris, P. Singh, and N. Komodakis, “Unsupervised representation learning by predicting image rotations,” in International Conference on Learning Representations, 2018. [Online]. Available: https: //openreview.net/forum?id=S1v4N2l0-

[10] C. Doersch, A. Gupta, and A. A. Efros, “Unsupervised visual representation learning by context prediction,” in Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1422-1430. [OpenAIRE]

[11] R. Zhang, P. Isola, and A. A. Efros, “Colorful image colorization,” in European conference on computer vision. Springer, 2016, pp. 649-666.

[12] J. Donahue, P. Kra¨henbu¨ hl, and T. Darrell, “Adversarial feature learning,” arXiv preprint arXiv:1605.09782, 2016.

[13] X. Wang and A. Gupta, “Unsupervised learning of visual representations using videos,” in Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 2794-2802.

[14] C. Vondrick, A. Shrivastava, A. Fathi, S. Guadarrama, and K. Murphy, “Tracking emerges by colorizing videos,” in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 391- 408. [OpenAIRE]

[15] E. Jang, C. Devin, V. Vanhoucke, and S. Levine, “Grasp2vec: Learning object representations from self-supervised grasping,” Conference on Robot Learning, 2018.

31 references, page 1 of 3
Abstract
In this work, we propose to learn local descriptors for point clouds in a self-supervised manner. In each iteration of the training, the input of the network is merely one unlabeled point cloud. On top of our previous work, that directly solves the transformation between two point sets in one step without correspondences, the proposed method is able to train from one point cloud, by supervising its self-rotation, that we randomly generate. The whole training requires no manual annotation. In several experiments we evaluate the performance of our method on various datasets and compare to other state of the art algorithms. The results show, that our self-supervise...
Subjects
arXiv: Computer Science::Machine Learning
ACM Computing Classification System: ComputingMethodologies_PATTERNRECOGNITION
free text keywords: Computer Science - Robotics
Related Organizations
Download from
31 references, page 1 of 3

[1] H. Durrant-Whyte and T. Bailey, “Simultaneous localization and mapping: part i,” IEEE robotics & automation magazine, vol. 13, no. 2, pp. 99-110, 2006.

[2] Y. Zhong, “A shape descriptor for 3d object recognition,” in Proceedings ICCV 2009 Workshop 3DRR, vol. 6, 2009.

[3] R. B. Rusu, N. Blodow, and M. Beetz, “Fast point feature histograms (fpfh) for 3d registration,” in 2009 IEEE international conference on robotics and automation. IEEE, 2009, pp. 3212-3217.

[4] 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.

[5] Z. Gojcic, C. Zhou, J. D. Wegner, and A. Wieser, “The perfect match: 3d point cloud matching with smoothed densities,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 5545-5554. [OpenAIRE]

[6] 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.

[7] Z. J. Yew and G. H. Lee, “3dfeat-net: Weakly supervised local 3d features for point cloud registration,” in European Conference on Computer Vision. Springer, 2018, pp. 630-646.

[8] A. Dosovitskiy, P. Fischer, J. T. Springenberg, M. Riedmiller, and T. Brox, “Discriminative unsupervised feature learning with exemplar convolutional neural networks,” IEEE transactions on pattern analysis and machine intelligence, vol. 38, no. 9, pp. 1734-1747, 2015.

[9] S. Gidaris, P. Singh, and N. Komodakis, “Unsupervised representation learning by predicting image rotations,” in International Conference on Learning Representations, 2018. [Online]. Available: https: //openreview.net/forum?id=S1v4N2l0-

[10] C. Doersch, A. Gupta, and A. A. Efros, “Unsupervised visual representation learning by context prediction,” in Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1422-1430. [OpenAIRE]

[11] R. Zhang, P. Isola, and A. A. Efros, “Colorful image colorization,” in European conference on computer vision. Springer, 2016, pp. 649-666.

[12] J. Donahue, P. Kra¨henbu¨ hl, and T. Darrell, “Adversarial feature learning,” arXiv preprint arXiv:1605.09782, 2016.

[13] X. Wang and A. Gupta, “Unsupervised learning of visual representations using videos,” in Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 2794-2802.

[14] C. Vondrick, A. Shrivastava, A. Fathi, S. Guadarrama, and K. Murphy, “Tracking emerges by colorizing videos,” in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 391- 408. [OpenAIRE]

[15] E. Jang, C. Devin, V. Vanhoucke, and S. Levine, “Grasp2vec: Learning object representations from self-supervised grasping,” Conference on Robot Learning, 2018.

31 references, page 1 of 3
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue