本文分享 CVPR 2022 论文『SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration』,二阶相似性测度,让传统配准方法取得比深度学习更好的性能,并达到深度学习的速度。
[1] Martin A Fischler and Robert C Bolles. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM.[2] Qian-Yi Zhou, Jaesik Park, and Vladlen Koltun. Fast global registration. In European Conference on Computer Vision, pages 766–782. Springer, 2016.[3] Siwen Quan and Jiaqi Yang. Compatibility-guided sampling consensus for 3-d point cloud registration. IEEE Transactions on Geoscience and Remote Sensing, 58(10):7380–7392, 2020.[4] Xuyang Bai, Zixin Luo, Lei Zhou, Hongkai Chen, Lei Li, Zeyu Hu, Hongbo Fu, and Chiew-Lan Tai. 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] Junha Lee, Seungwook Kim, Minsu Cho, and Jaesik Park. Deep hough voting for robust global registration. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 15994–16003, 2021.