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

Download

index.pdf

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

332
views

237
downloads

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

Suggestions

OpenMETU
Core

Supervised mesh segmentation for 3D objects with graph Convolutional neural networks Perek, Emir Kaan; Sahillioğlu, Yusuf; Department of Computer Engineering (2019) Mesh segmentation is a fundamental application that is primarily used for understanding and analyzing 3D shapes in a broad range of areas in Computer Science. With the increasing trend of deep learning, there have been many learning-based solutions to the mesh segmentation problem based on the classification of the individual mesh polygons. In this thesis, we cast mesh segmentation as a supervised graph labeling problem by using Graph Convolutional Neural Networks (GCNN). We treat a mesh object as a graph t...
Geospatial Object Detection Using Deep Networks Barut, Onur; Alatan, Abdullah Aydın (2019-01-01) In the last decade, deep learning has been drawing a huge interest due to the developments in the computational hardware and novel machine learning techniques. This progress also significantly effects satellite image analysis for various objectives, such as disaster and crisis management, forest cover, road mapping, city planning and even military purposes. For all these applications, detection of geospatial objects has crucial importance and some recent object detection techniques are still unexplored to b...
Geospatial object recognition using deep networks for satellite images Barut, Onur; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2018) Deep learning paradigm has been drawing significant interest during the last decade due to the recent developments in novel machine learning algorithms and improvements in computational hardware. Satellite image analysis is also an important scientific area with many objectives, such as disaster and crisis management, forest cover, road mapping, city planning, even military purposes. Spatial correlations of land cover or geospatial objects between different images lead to widely utilization of convolutional...
Neural networks with piecewise constant argument and impact activation Yılmaz, Enes; Akhmet, Marat; Department of Scientific Computing (2011) This dissertation addresses the new models in mathematical neuroscience: artificial neural networks, which have many similarities with the structure of human brain and the functions of cells by electronic circuits. The networks have been investigated due to their extensive applications in classification of patterns, associative memories, image processing, artificial intelligence, signal processing and optimization problems. These applications depend crucially on the dynamical behaviors of the networks. In t...
Case studies on the use of neural networks in eutrophication modeling Karul, C; Soyupak, S; Cilesiz, AF; Akbay, N; Germen, E (2000-10-30) Artificial neural networks are becoming more and more common to be used in development of prediction models for complex systems as the theory behind them develops and the processing power of computers increase. A three layer Levenberg-Marquardt feedforward learning algorithm was used to model the eutrophication process in three water bodies of Turkey (Keban Dam Reservoir, Mogan and Eymir Lakes). Despite the very complex and peculiar nature of Keban Dam, a relatively good correlation (correlation coefficient...

Citation Formats

Ö. İ. Sever, “Mesh segmentation from sparse face labels using graph convolutional neural networks.,” Thesis (M.S.) -- Graduate School of Natural and Applied Sciences. Computer Engineering., Middle East Technical University, 2020.