Data-driven Pixel Filter Aware MIP Maps for SVBRDFs

Loading...
Thumbnail Image
Journal Title
Journal ISSN
Volume Title
Conference article in proceedings
This publication is imported from Aalto University research portal.
View publication in the Research portal
View/Open full text file from the Research portal
Date
2023
Major/Subject
Mcode
Degree programme
Language
en
Pages
51-61
Series
Eurographics Symposium on Rendering
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.
Description
Keywords
Other note
Citation
Kemppinen , P , Aittala , M & Lehtinen , J 2023 , Data-driven Pixel Filter Aware MIP Maps for SVBRDFs . in T Ritschel & A Weidlich (eds) , Eurographics Symposium on Rendering . Eurographics Association , pp. 51-61 , Eurographics Symposium on Rendering , Delft , Netherlands , 28/06/2023 . https://doi.org/10.2312/sr.20231124