Abstract
Deep learning for 3D data has become a popular research theme in many fields. However, most of the research on 3D data is based on voxels, 2D images, and point clouds. At actual industrial sites, face-based geometry data are being used, but their direct application to industrial sites remains limited due to a lack of existing research. In this study, to overcome these limitations, we present a face-based variational autoencoder (FVAE) model that generates 3D geometry data using a variational autoencoder (VAE) model directly from face-based geometric data. Our model improves the existing node and edge-based adjacency matrix and optimizes it for geometric learning by using a face- and edge-based adjacency matrix according to the 3D geometry structure. In the experiment, we achieved the result of generating adjacency matrix information with 72% precision and 69% recall through end-to-end learning of Face-Based 3D Geometry. In addition, we presented various structurization methods for 3D unstructured geometry and compared their performance, and proved the method to effectively perform reconstruction of the learned structured data through experiments.
Highlights
Deep learning for 3D data is being researched in various fields because of its great utility
True Positive (TP): Exists in the input voxel and exists in the output voxel; True Negative (TN): When it does not exist in the input voxel and does not exist in the output voxel; False Positive (FP): If it does not exist in the input voxel, but exists in the output voxel; False Negative(FN) : Exists in the input voxel and not in the output voxel
We presented a face-based variational autoencoders (FVAE) model that generates 3D geometric data
Summary
Deep learning for 3D data is being researched in various fields because of its great utility. 3D data exist in various forms, such as 2D images, voxels, point clouds, and polygon models, and deep learning research is being conducted based on these various data. As the research is being conducted mainly on 2D images [1,2,3,4,5,6], voxels [1,7,8,9,10,11], and point clouds [12,13,14], which are relatively easy to learn, there is a limit to directly applying the research results in actual industrial sites as the commonly used. We achieved the result of generating adjacency matrix information with 72% precision and 69% recall through endto-end learning with vertex position and face index data, which are basic geometries
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.
