MatUp: Repurposing Image Upsamplers for SVBRDFs
No Thumbnail Available
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
We propose MATUP, an upsampling filter for material super-resolution. Our method takes as input a low-resolution SVBRDF and upscales its maps so that their rendering under various lighting conditions fits upsampled renderings inferred in the radiance domain with pre-trained RGB upsamplers. We formulate our local filter as a compact Multilayer Perceptron (MLP), which acts on a small window of the input SVBRDF and is optimized using a data-fitting loss defined over upsampled radiance at various locations. This optimization is entirely performed at the scale of a single, independent material. Doing so, MATUP leverages the reconstruction capabilities acquired over large collections of natural images by pre-trained RGB models and provides regularization over self-similar structures. In particular, our light-weight neural filter avoids retraining complex architectures from scratch or accessing any large collection of low/high resolution material pairs - which do not actually exist at the scale RGB upsamplers are trained with. As a result, MATUP provides fine and coherent details in the upscaled material maps, as shown in the extensive evaluation we provide.
Description
CCS Concepts: Computing methodologies → Reflectance modeling; Texturing
@article{10.1111:cgf.15151,
journal = {Computer Graphics Forum},
title = {{MatUp: Repurposing Image Upsamplers for SVBRDFs}},
author = {Gauthier, Alban and Kerbl, Bernhard and Levallois, Jérémy and Faury, Robin and Thiery, Jean-Marc and Boubekeur, Tamy},
year = {2024},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.15151}
}