RoCNet: 3D Robust Registration of Point-Clouds using Deep Learning
Not on the map. Why?
Abstract (arXiv)
This paper introduces a new method for 3D point cloud registration based on deep learning. The architecture is composed of three distinct blocs: (i) an encoder composed of a convolutional graph-based descriptor that encodes the immediate neighbourhood of each point and an attention mechanism that encodes the variations of the surface normals. Such descriptors are refined by highlighting attention between the points of the same set and then between the points of the two sets. (ii) a matching process that estimates a matrix of correspondences using the Sinkhorn algorithm. (iii) Finally, the rigid transformation between the two point clouds is calculated by RANSAC using the Kc best scores from the correspondence matrix. We conduct experiments on the ModelNet40 dataset, and our proposed architecture shows very promising results, outperforming state-of-the-art methods in most of the simulated configurations, including partial overlap and data augmentation with Gaussian noise.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 21 of its 32 references that are in the map. First posted on arXiv 14 Mar 2023.
Builds on
21 of 32 references.
References · 21
- 2017Attention Is All You Needcited by 60,361
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
- 2020Point Transformercited by 1,470
- 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
- 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 321
- 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 290
- 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 233
- 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 202
- 2020D3Feat: Joint Learning of Dense Detection and Description of 3D Local Featurescited by 177
9 more
- 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
- 20183DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registrationcited by 103
- 2018Unsupervised Deep Learning for Structured Shape Matchingcited by 81
- 20203D Point Cloud Processing and Learning for Autonomous Drivingcited by 68
- 2017Learning Compact Geometric Featurescited by 45
- 2021UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Renderingcited by 44
- 2021R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Methodcited by 26
- 2022VRNet: Learning the Rectified Virtual Corresponding Points for 3D Point Cloud Registrationcited by 8
- 2021WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registrationcited by 7
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.