Flexible SVBRDF Capture with a Multi‐Image Deep Network
Name
1906.11557.pdf
Description
Accepted version
Size
7.08 MB
Format
Adobe PDF
Checksum (MD5)
a71346b118b9c94fb23c59feaf7a01f5
Author(s)
Aittala, Miika
Durand, Fredo
Date Issued
July 2019
Journal
Computer Graphics Forum
Publisher
Wiley
Citation
Deschaintre, Valentin et al. “Flexible SVBRDF Capture with a Multi‐Image Deep Network.” Computer Graphics Forum, 38, 4 (July 2019) © 2019 The Author(s)
Version
Author's final manuscript
Abstract
Empowered by deep learning, recent methods for material capture can estimate a spatially-varying reflectance from a single photograph. Such lightweight capture is in stark contrast with the tens or hundreds of pictures required by traditional optimization-based approaches. However, a single image is often simply not enough to observe the rich appearance of real-world materials. We present a deep-learning method capable of estimating material appearance from a variable number of uncalibrated and unordered pictures captured with a handheld camera and flash. Thanks to an order-independent fusing layer, this architecture extracts the most useful information from each picture, while benefiting from strong priors learned from data. The method can handle both view and light direction variation without calibration. We show how our method improves its prediction with the number of input pictures, and reaches high quality reconstructions with as little as 1 to 10 images - a sweet spot between existing single-image and complex multi-image approaches.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1111/CGF.13765
