Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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.

G. Dias Pais, Srikumar Ramalingam, Venu Madhav Govindu, Jacinto C. Nascimento, Rama Chellappa, Pedro Miraldo• 2019

Related benchmarks

TaskDatasetResultRank
Point cloud registration3DMatch (test)
Registration Recall77.8
339
Point cloud registration3DMatch
Registration Recall (RR)77.76
51
Point cloud registration3DMatch FPFH descriptors
RR26.31
11
Point cloud registration3DMatch FCGF descriptors
Registration Recall (%)77.76
11
Showing 4 of 4 rows

Other info

Follow for update