Supervised mesh segmentation for 3D objects with graph Convolutional neural networks

Download
2019
Perek, Emir Kaan
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 to be labeled and develop a segmentation model that takes an entire structure of the object as input and returns its segmentation. While similar models focus on labeling each polygon of the 3D objects separately, our model is capable of labeling all polygons in a single run thanks to GCNN. Moreover, being able to use connectivity information in the graph provides an opportunity for a drastic decrease in the required features used as input to the model, compared to the previous studies. We train and test our model for segmenting human shapes, one of the challenging shapes to segment. We report competitive results compared to other state-of-art supervised segmentation techniques by using noticeably less input features.

Suggestions

Mesh segmentation from sparse face labels using graph convolutional neural networks.
Sever, Önder İlke; Sahillioğlu, Yusuf; Department of Computer Engineering (2020)
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 ...
Image segmentation with unified region and boundary characteristics within recursive shortest spanning tree
Esen, E.; Alp, Y. K. (2007-06-13)
The lack of boundary information in region based image segmentation algorithms resulted in many hybrid methods that integrate the complementary information sources of region and boundary, in order to increase the segmentation performance. In compliance with this trend, we propose a novel method to unify the region and boundary characteristics within the canonical Recursive Shortest Spanning Tree algorithm. The main idea is to incorporate the boundary information in the distance metric of RSST with minor cha...
UTILIZATION OF SPATIAL INFORMATION FOR POINT CLOUD SEGMENTATION
Akman, Oytun; Bayramoglu, Neslihan; Alatan, Abdullah Aydın; Jonker, Pieter (2010-06-09)
Object segmentation has an important role in the field of computer vision for semantic information inference. Many applications such as 3DTV archive systems, 3D/2D model fitting, object recognition and shape retrieval are strongly dependent to the performance of the segmentation process. In this paper we present a new algorithm for object localization and segmentation based on the spatial information obtained via a Time-of-Flight (TOF) camera. 3D points obtained via a TOF camera are projected onto the major...
Recursive shortest spanning tree algorithms for image segmentation
Bayramoglu, NY; Bazlamaçcı, Cüneyt Fehmi (2005-11-24)
Image segmentation has an important role in image processing and the speed of the segmentation algorithm may become a drawback for some applications. This study analyzes the run time performances of some variations of the Recursive Shortest Spanning Tree Algorithm (RSST) and proposes simple but effective modifications on these algorithms to improve their speeds. In addition, the effect of link weight cost function on the run time performance and the segmentation quality is examined. For further improvement ...
Edge strength functions as shape priors in image segmentation
Erdem, Erkut; Erdem, Aykut; Tarı, Zehra Sibel (2005-12-01)
Many applications of computer vision requires segmenting out of an object of interest from a given image. Motivated by unlevel-sets formulation of Raviv, Kiryati and Sochen [8] and statistical formulation of Leventon, Grimson and Faugeras [6], we present a new image segmentation method which accounts for prior shape information. Our method depends on Ambrosio-Tortorelli approximation of Mumford-Shah functional. The prior shape is represented by a by-product of this functional, a smooth edge indicator functi...
Citation Formats
E. K. Perek, “Supervised mesh segmentation for 3D objects with graph Convolutional neural networks,” Thesis (M.S.) -- Graduate School of Natural and Applied Sciences. Computer Engineering., Middle East Technical University, 2019.