Generative Modelling of BRDF Textures from Flash Images

Advanced search
Browse by:

Department | Year

UCL Theses | Latest

Deposit your research

Generative Modelling of BRDF Textures from Flash Images

Henzler, Philipp; Deschaintre, Valentin; Mitra, Niloy J; Ritschel, Tobias; (2021) Generative Modelling of BRDF Textures from Flash Images. ACM Transactions on Graphics , 40 (6) , Article 284. 10.1145/3478513.3480507. Green open access

Preview

PDF
brdf.pdf - Accepted Version
Download (12MB) | Preview

Abstract

We learn a latent space for easy capture, consistent interpolation, and efficient reproduction of visual material appearance. When users provide a photo of a stationary natural material captured under flashlight illumination, first it is converted into a latent material code. Then, in the second step, conditioned on the material code, our method produces an infinite and diverse spatial field of BRDF model parameters (diffuse albedo, normals, roughness, specular albedo) that subsequently allows rendering in complex scenes and illuminations, matching the appearance of the input photograph. Technically, we jointly embed all flash images into a latent space using a convolutional encoder, and -conditioned on these latent codes- convert random spatial fields into fields of BRDF parameters using a convolutional neural network (CNN). We condition these BRDF parameters to match the visual characteristics (statistics and spectra of visual features) of the input under matching light. A user study compares our approach favorably to previous work, even those with access to BRDF supervision. Project webpage: https://henzler.github.io/publication/neuralmaterial/.

Type:	Article
Title:	Generative Modelling of BRDF Textures from Flash Images
Open access status:	An open access version is available from UCL Discovery
DOI:	10.1145/3478513.3480507
Publisher version:	https://doi.org/10.1145/3478513.3480507
Language:	English
Additional information:	This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords:	Science & Technology, Technology, Computer Science, Software Engineering, Computer Science, material capture, appearance capture, SVBRDF, deep learning, generative model, unsupervised learning, ILLUMINATION, REFLECTANCE
UCL classification:	UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI:	https://discovery.ucl.ac.uk/id/eprint/10159070