Data-driven Pixel Filter Aware MIP Maps for SVBRDFs

Pauli Kemppinen, Miika Aittala, Jaakko Lehtinen

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

9 Lataukset (Pure)


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.
OtsikkoEurographics Symposium on Rendering
ToimittajatTobias Ritschel, Andrea Weidlich
KustantajaEurographics Association
ISBN (painettu)978-3-03868-229-5
DOI - pysyväislinkit
TilaJulkaistu - 2023
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaEurographics Symposium on Rendering - Delft, Alankomaat
Kesto: 28 kesäk. 202330 kesäk. 2023
Konferenssinumero: 34


ConferenceEurographics Symposium on Rendering


Sukella tutkimusaiheisiin 'Data-driven Pixel Filter Aware MIP Maps for SVBRDFs'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä