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.
3DRegNet: A Deep Neural Network for 3D Point Registration
3DRegNet, a novel deep learning architecture, addresses 3D scan registration challenges by classifying point correspondences and regressing motion parameters, outperforming baselines with a refinement network.
- Year
- 2019
- Venue
- 3dregnet-a-deep-neural-network-for-3d-point-1
- Authors
- 6
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/1904.01701v2ARXIV-DEFAULT
- TL;DR
- Semantic Scholar