Learning non-stationary SVBRDFs using GANs and differentiable rendering

In this thesis we propose a learning approach for generating realistic SVBRDFs using generative adversarial models and differentiable rendering. Our model learns a mapping from the geometry buffer of a surface to a corresponding albedo texture-map by training on images of the same surface rendered using a target texture-map. A key feature of this learning process is the ability to differentiate the render function within our model; this enables the optimization of the texture-map generator parameters using a loss function computed from the rendered 2D images. Our results show that differentiable rendering is applicable in complex neural network models such as GANs, opening up opportunities for more applications of deep learning methods in the computer graphics pipeline.

Name thesis:degree_name

Master

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2019

Author dc:creator

• Duinkharjav, Budmonde.

Advisor dc:contributor.advisor

• Frédo Durand.

• Electrical Engineering and Computer Science.

Statement dc:rights

• MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.

Licence dc:rights.uri

• http://dspace.mit.edu/handle/1721.1/7582

Language dc:language.iso

eng

Handle dc:identifier.uri

https://hdl.handle.net/1721.1/123018

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/123018