Mesh segmentation from sparse face labels using graph convolutional neural networks.

Date

2020

Author

Sever, Önder İlke

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

27
views

34
downloads

Cite This

The marked improvements in deep learning influence almost every area of computer science. The mesh segmentation problem in computer graphics has been an active research area and keep abreast of the trend of deep learning developments. The mesh segmentation has a central role in multiple application areas for 3D objects. It is chiefly used to produce the object structure in order to manipulate the object or analyze the components of it. These operations are primitive, and that primitiveness causes a variety of application areas. The variation in application areas induce a variety of priority deviations over time and memory usage. In this thesis, we solve the mesh segmentation problem by using Graph Convolutional Neural Networks. Our method uses a semi-supervised approach for which the mesh objects are sparsely labeled, and the results are the formed segments. We consider a mesh object as a graph by using their connectedness over the faces, and having the mesh in 3D lets us create geometrically logical features for our network. Using the neighborhood information is maintained by the Graph Convolutional Neural Networks, which is a pretty new concept, and the application on the sparsely labeled mesh segmentation is novel to our work. By using the briefly summarized method, we reach competitive results compared to state-of-art mesh segmentation methods.

Subject Keywords

Neural networks (Computer science)., Keywords: 3D, mesh, segmentation, semi-supervised learning, graph convolutional neural networks

URI

http://etd.lib.metu.edu.tr/upload/12625266/index.pdf
https://hdl.handle.net/11511/45555

Collections

Graduate School of Natural and Applied Sciences, Thesis