Automatically generating textured buildings using reconstructive and statistical methods
Author(s)
Lee, Ka Wai,M. Eng.Massachusetts Institute of Technology.
Download1129384696-MIT.pdf (7.538Mb)
Other Contributors
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Advisor
Frédo Durand.
Terms of use
Metadata
Show full item recordAbstract
Realistic 3D models of cities are extremely important for generating synthetic datasets for deep learning models. Current algorithms generate models of cities that are either monotonous, unrealistic, or must be specified with many procedural rules. In this thesis we present AutoCity, a system for generating realistic textured buildings given only the footprints of the buildings. AutoCity generates buildings using reconstructive and procedural methods, and then textures the buildings using a known adversarial neural network, FrankenGAN. We provide images of our output and extensive documentation on how the system can be run and extended.
Description
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 45-46).
Date issued
2019Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer SciencePublisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.