Print Email Facebook Twitter Procedural Tree Generation Title Procedural Tree Generation: How to efficiently predict branching structures from foliage? Author Taklimi, Sam (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Eisemann, E. (mentor) Kellnhofer, P. (mentor) Uzolas, L. (mentor) Reinders, M.J.T. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2024-02-02 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. Subject Computer GraphicsGenerative Adverserial Networks (GANs)Image to Image transformationConvolutional Neural Networks (CNNs) To reference this document use: http://resolver.tudelft.nl/uuid:433be09a-c741-421a-9b14-2929f2318d62 Part of collection Student theses Document type bachelor thesis Rights © 2024 Sam Taklimi Files PDF Sam-Taklimi-final-version.pdf 1.36 MB Close viewer /islandora/object/uuid:433be09a-c741-421a-9b14-2929f2318d62/datastream/OBJ/view