Procedural Tree Generation

Taklimi, A.

Procedural Tree Generation

How to efficiently predict branching structures from foliage?

Bachelor thesis (2024)

Authors

A. Taklimi Electrical Engineering, Mathematics and Computer Science

Contributors

E. Eisemann Computer Graphics and Visualisation (mentor)

P. Kellnhofer Computer Graphics and Visualisation (mentor)

L. Uzolas Computer Graphics and Visualisation (mentor)

Marcel Reinders Pattern Recognition and Bioinformatics (graduation committee member)

Faculty

Electrical Engineering, Mathematics and Computer Science, Electrical Engineering, Mathematics and Computer Science

Computer Graphics Convolutional Neural Networks (CNNs) Generative Adverserial Networks (GANs) Image to Image transformation

To reference this document use:

http://resolver.tudelft.nl/uuid:433be09a-c741-421a-9b14-2929f2318d62

More Info

expand_more

Published Date

02-02-2024

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

The objective of this project is to train a model that transforms a tree with its foliage into only its branch structure. This is achieved by employing machine-learning techniques, specifically Generative Adverserial Networks (GANs). By utilizing the proposed method, a predictive model is built that automatically minimizes its own error function through a comparison of a set of input and ground-truth tree images, which are tree images with and without leaves, respectively. The adoption of GANs has shown promising results, both visually and metrically.

Files

Sam-Taklimi-final-version.pdf

(pdf | 1.36 Mb)

Unknown license