3DRegNet: A Deep Neural Network for 3D Point Registration
About
We present 3DRegNet, a novel deep learning architecture for the registration of 3D scans. Given a set of 3D point correspondences, we build a deep neural network to address the following two challenges: (i) classification of the point correspondences into inliers/outliers, and (ii) regression of the motion parameters that align the scans into a common reference frame. With regard to regression, we present two alternative approaches: (i) a Deep Neural Network (DNN) registration and (ii) a Procrustes approach using SVD to estimate the transformation. Our correspondence-based approach achieves a higher speedup compared to competing baselines. We further propose the use of a refinement network, which consists of a smaller 3DRegNet as a refinement to improve the accuracy of the registration. Extensive experiments on two challenging datasets demonstrate that we outperform other methods and achieve state-of-the-art results. The code is available.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Point cloud registration | 3DMatch (test) | Registration Recall77.8 | 339 | |
| Point cloud registration | 3DMatch | Registration Recall (RR)77.76 | 51 | |
| Point cloud registration | 3DMatch FPFH descriptors | RR26.31 | 11 | |
| Point cloud registration | 3DMatch FCGF descriptors | Registration Recall (%)77.76 | 11 |