Gaussian material synthesis

Zsolnai-Fehér, Károly; Wonka, Peter; Wimmer, Michael

dc.contributor.author	Zsolnai-Fehér, Károly
dc.contributor.author	Wonka, Peter
dc.contributor.author	Wimmer, Michael
dc.date.accessioned	2018-12-23T08:06:03Z
dc.date.available	2018-12-23T08:06:03Z
dc.date.issued	2018-07-31
dc.identifier.citation	Zsolnai-Fehér K, Wonka P, Wimmer M (2018) Gaussian material synthesis. ACM Transactions on Graphics 37: 1–14. Available: http://dx.doi.org/10.1145/3197517.3201307.
dc.identifier.issn	0730-0301
dc.identifier.doi	10.1145/3197517.3201307
dc.identifier.uri	http://hdl.handle.net/10754/630344
dc.description.abstract	We present a learning-based system for rapid mass-scale material synthesis that is useful for novice and expert users alike. The user preferences are learned via Gaussian Process Regression and can be easily sampled for new recommendations. Typically, each recommendation takes 40-60 seconds to render with global illumination, which makes this process impracticable for real-world workflows. Our neural network eliminates this bottleneck by providing high-quality image predictions in real time, after which it is possible to pick the desired materials from a gallery and assign them to a scene in an intuitive manner.Workflow timings against Disney's
dc.description.sponsorship	We would like to thank Robin Marin for the material test scene and Vlad Miller for his help with geometry modeling, Felícia Zsolnai–Fehér for improving the design of many figures, Hiroyuki Sakai, Christian Freude, Johannes Unterguggenberger, Pranav Shyam and Minh Dang for their useful comments, and Silvana Podaras for her help with a previous version of this work.We also thank NVIDIA for providing the GPU used to train our neural networks. This work was partially funded by Austrian Science Fund (FWF), project number P27974. Scene and geometry credits: Gold Bars – JohnsonMartin, Christmas Ornaments – oenvoyage, Banana – sgamusse, Bowl – metalix, Grapes – PickleJones, Glass Fruits – BobReed64, Ice cream – b2przemo, Vases – Technausea, Break Time – Jay–Artist, Wrecking Ball – floydkids, Italian Still Life – aXel, Microplanet – marekv, Microplanet vegetation – macio.
dc.publisher	Association for Computing Machinery (ACM)
dc.relation.url	https://dl.acm.org/citation.cfm?doid=3197517.3201307
dc.rights	© ACM, 2018. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ACM Transactions on Graphics, {37, 4, (2018-07-31)} http://doi.acm.org/10.1145/3197517.3201307
dc.subject	Gaussian process regression
dc.subject	latent variables
dc.subject	neural networks
dc.subject	neural rendering
dc.subject	photorealistic rendering
dc.title	Gaussian material synthesis
dc.type	Article
dc.contributor.department	Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.department	Computer Science Program
dc.contributor.department	Visual Computing Center (VCC)
dc.identifier.journal	ACM Transactions on Graphics
dc.eprint.version	Post-print
dc.contributor.institution	TU Wien, Vienna, Austria
dc.identifier.arxivid	1804.08369
kaust.person	Wonka, Peter
dc.version	v1
refterms.dateFOA	2018-12-23T08:25:42Z
dc.date.published-online	2018-07-31
dc.date.published-print	2018-07-30
dc.date.posted	2018-04-23