BranchNet: Tree Modeling with Hierarchical Graph Networks

Research on modeling trees and plants has attracted a great deal of attention in recent years. Early procedural tree modeling can be divided into four main categories: rule-based algorithms, repetitive patterns, cellular automata, and particle systems. These methods offer a very high level of rea...

Full description

Bibliographic Details
Main Author: Zhang, Jiayao
Other Authors: Michels, Dominik L.
Language:en
Published: 2021
Subjects:
Online Access:Zhang, J. (2021). BranchNet: Tree Modeling with Hierarchical Graph Networks. KAUST Research Repository. https://doi.org/10.25781/KAUST-OFB09
http://hdl.handle.net/10754/670111
id ndltd-kaust.edu.sa-oai-repository.kaust.edu.sa-10754-670111
record_format oai_dc
spelling ndltd-kaust.edu.sa-oai-repository.kaust.edu.sa-10754-6701112021-07-14T05:09:49Z BranchNet: Tree Modeling with Hierarchical Graph Networks Zhang, Jiayao Michels, Dominik L. Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division Wonka, Peter Elhoseiny, Mohamed H. Graph Neural Network Tree Modeling L-system Research on modeling trees and plants has attracted a great deal of attention in recent years. Early procedural tree modeling can be divided into four main categories: rule-based algorithms, repetitive patterns, cellular automata, and particle systems. These methods offer a very high level of realism; however, creating millions of varied tree datasets manually is not logistically possible, even for professional 3D modeling artists. Trees created using these previous methods are typically static and the controllability of these procedural tree models is low. Deep generative models are capable of generating any type of shape automatically, making it possible to create 3D models at large scale. In this paper, we introduce a novel deep generative model that generates 3D (botanical) tree models, which are not only edible, but also have diverse shapes. Our proposed network, denoted BranchNet, trains the tree branch structures on a hierarchical Variational Autoencoder (VAE) that learns new generative model structures. By directly encoding shapes into a hierarchy graph, BranchNet can generate diverse, novel, and realistic tree structures. To assist the creation of tree models, we create a domain-specific language with a GUI for modeling 3D shape structures, in which the continuous parameters can be manually edited in order to produce new tree shapes. The trees are interpretable and the GUI can be edited to capture the subset of shape variability. 2021-07-11T11:17:04Z 2021-07-11T11:17:04Z 2021-07-04 Thesis Zhang, J. (2021). BranchNet: Tree Modeling with Hierarchical Graph Networks. KAUST Research Repository. https://doi.org/10.25781/KAUST-OFB09 10.25781/KAUST-OFB09 http://hdl.handle.net/10754/670111 en
collection NDLTD
language en
sources NDLTD
topic Graph Neural Network
Tree Modeling
L-system
spellingShingle Graph Neural Network
Tree Modeling
L-system
Zhang, Jiayao
BranchNet: Tree Modeling with Hierarchical Graph Networks
description Research on modeling trees and plants has attracted a great deal of attention in recent years. Early procedural tree modeling can be divided into four main categories: rule-based algorithms, repetitive patterns, cellular automata, and particle systems. These methods offer a very high level of realism; however, creating millions of varied tree datasets manually is not logistically possible, even for professional 3D modeling artists. Trees created using these previous methods are typically static and the controllability of these procedural tree models is low. Deep generative models are capable of generating any type of shape automatically, making it possible to create 3D models at large scale. In this paper, we introduce a novel deep generative model that generates 3D (botanical) tree models, which are not only edible, but also have diverse shapes. Our proposed network, denoted BranchNet, trains the tree branch structures on a hierarchical Variational Autoencoder (VAE) that learns new generative model structures. By directly encoding shapes into a hierarchy graph, BranchNet can generate diverse, novel, and realistic tree structures. To assist the creation of tree models, we create a domain-specific language with a GUI for modeling 3D shape structures, in which the continuous parameters can be manually edited in order to produce new tree shapes. The trees are interpretable and the GUI can be edited to capture the subset of shape variability.
author2 Michels, Dominik L.
author_facet Michels, Dominik L.
Zhang, Jiayao
author Zhang, Jiayao
author_sort Zhang, Jiayao
title BranchNet: Tree Modeling with Hierarchical Graph Networks
title_short BranchNet: Tree Modeling with Hierarchical Graph Networks
title_full BranchNet: Tree Modeling with Hierarchical Graph Networks
title_fullStr BranchNet: Tree Modeling with Hierarchical Graph Networks
title_full_unstemmed BranchNet: Tree Modeling with Hierarchical Graph Networks
title_sort branchnet: tree modeling with hierarchical graph networks
publishDate 2021
url Zhang, J. (2021). BranchNet: Tree Modeling with Hierarchical Graph Networks. KAUST Research Repository. https://doi.org/10.25781/KAUST-OFB09
http://hdl.handle.net/10754/670111
work_keys_str_mv AT zhangjiayao branchnettreemodelingwithhierarchicalgraphnetworks
_version_ 1719416553452077056