Data-driven Pixel Filter Aware MIP Maps for SVBRDFs
Abstract
We propose a data-driven approach for generating MIP map pyramids from SVBRDF parameter maps. We learn a latent material representation where linear image downsampling corresponds to linear prefiltering of surface reflectance. In contrast to prior work, we explicitly model the effect of the antialiasing pixel filter also at the finest resolution. This yields high-quality results even in images that are shaded only once per pixel with no further processing. The SVBRDF maps produced by our method can be used as drop-in replacements within existing rendering systems, and the data-driven nature of our framework makes it possible to change the shading model with little effort. As a proof of concept, we also demonstrate using a shared latent representation for two different shading models, allowing for automatic conversion
BibTeX
@inproceedings {10.2312:sr.20231124,
booktitle = {Eurographics Symposium on Rendering},
editor = {Ritschel, Tobias and Weidlich, Andrea},
title = {{Data-driven Pixel Filter Aware MIP Maps for SVBRDFs}},
author = {Kemppinen, Pauli and Aittala, Miika and Lehtinen, Jaakko},
year = {2023},
publisher = {The Eurographics Association},
ISSN = {1727-3463},
ISBN = {978-3-03868-229-5},
DOI = {10.2312/sr.20231124}
}
booktitle = {Eurographics Symposium on Rendering},
editor = {Ritschel, Tobias and Weidlich, Andrea},
title = {{Data-driven Pixel Filter Aware MIP Maps for SVBRDFs}},
author = {Kemppinen, Pauli and Aittala, Miika and Lehtinen, Jaakko},
year = {2023},
publisher = {The Eurographics Association},
ISSN = {1727-3463},
ISBN = {978-3-03868-229-5},
DOI = {10.2312/sr.20231124}
}