Abstract
Invariance against rotation of 3D objects is one of the essential properties for 3D shape analysis. Recently proposed algorithms have achieved rotationally invariant 3D point set analysis by using inherently rotation-invariant 3D shape features, i.e., distances and angles among 3D points, as input to Deep Neural Networks (DNNs). The DNNs capture spatial hierarchy and context among the geometric features to produce accurate analytical results. In this article, we delve further into the DNN-based approach to rotation-invariant and highly accurate 3D point set analysis. In particular, we focus our attention on segmentation of 3D point sets, which is one of the most challenging among 3D point set analysis tasks. We propose a novel DNN for 3D point set segmentation called Rotation-invariant and Multi-scale feature Graph convolutional neural network, or RMGnet. Our RMGnet is more flexible than the previous methods as it accepts as input any handcrafted 3D shape features having rotation invariance. In addition, to accurately segment 3D point sets composed of parts having various sizes, we randomize scales at which handcrafted features are extracted and perform multi-resolution analysis of the features by using the DNN. Experimental evaluation demonstrates high segmentation accuracy as well as rotation invariance of the proposed RMGnet.
Highlights
Technology for 3D shape analysis has made a remarkable progress due in large part to advances in deep learning techniques and prevalence of 3D shape acquisition devices
RMGnet is trained by using the training set and segmentation accuracy is evaluated by using the testing set
It is worth noting that such high segmentation accuracy can be obtained by the point pair features commonly adopted by the previous studies and by the LRF-based 3D shape features. These results suggest that our approach, i.e., forming and analyzing rotation invariant and multi-scale feature graphs, is reasonable for rotationally invariant 3D point set segmentation
Summary
Technology for 3D shape analysis has made a remarkable progress due in large part to advances in deep learning techniques and prevalence of 3D shape acquisition devices. T. Furuya et al.: Convolution on RMG for 3D Point Set Segmentation previous studies, [10]–[13] adopt distances and/or angles computed from pairs of the 3D points as the input feature to the DNN. 3D shape analysis literature includes rotation-invariant handcrafted local features that describe local geometry of 3D point set by using methods other than distances and/or angles [15], [16].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
