Dias Pais, G and Ramalingam, S and Govindu, VM and Nascimento, JC and Chellappa, R and Miraldo, P (2020) 3DRegNet: A Deep Neural Network for 3D Point Registration. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 14 - 19 June 2020, Virtual, Online, pp. 7191-7201.
|
PDF
CVPR 2020.pdf.pdf - Published Version Download (7MB) | Preview |
Abstract
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. © 2020 IEEE.
Item Type: | Conference Paper |
---|---|
Publication: | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
Publisher: | IEEE Computer Society |
Additional Information: | The copyright for this article belongs to the Authors. |
Keywords: | Deep learning; Deep neural networks; Pattern recognition, 3-d scans; Learning architectures; Motion parameters; Point correspondence; Procrustes; Reference frame; State of the art, Neural networks |
Department/Centre: | Division of Electrical Sciences > Electrical Engineering |
Date Deposited: | 24 Jan 2023 04:32 |
Last Modified: | 24 Jan 2023 04:32 |
URI: | https://eprints.iisc.ac.in/id/eprint/79297 |
Actions (login required)
View Item |