0569632 20240402213643.420230306235959.9 10.5220/0011616200003417 8 s. P cav_un_epca*0569631978-989-758-634-72184-4321162-169LisbonSciTePress2023SousaA. AugustoBashford-RogersThomasBouatouchKadi Anisotropic BRDF models neural network activation function BTF cav_un_auth*0101165 Mikeš Stanislav UTIA-B Rozpoznávání obrazu Department of Pattern Recognition RO RO Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101093 Haindl Michal UTIA-B Rozpoznávání obrazu Department of Pattern Recognition RO RO Department of Pattern Recognition Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2023/RO/mikes-0569632.pdf GA19-12340S GA ČR CZ cav_un_auth*0376011 We present simple and fast neural anisotropic Bidirectional Reflectance Distribution Function (NN-BRDF) efficient models, capable of accurately estimating unmeasured combinations of illumination and viewing angles from sparse Bidirectional Texture Function (BTF) measurement of neighboring points in the illumination/viewing hemisphere. Our models are optimized for the best-performing activation function from nineteen widely used nonlinear functions and can be directly used in rendering. We demonstrate that the activation function significantly influences the modeling precision. The models enable us to reach significant time and cost-saving in not trivial and costly BTF measurements while maintaining acceptably low modeling error. The presented models learn well, even from only three percent of the original BTF measurements, and we can prove this by precise evaluation of the modeling error, which is smaller than the errors of alternative analytical BRDF models. cav_un_auth*0446965 International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - GRAPP 2023 /18./ 20230219 20230221 Lisbon PT BD 20000 20200 20205 2024 2 PR RVO:67985556 https://hdl.handle.net/11104/0341255 S 8 7.43 2023 SCOPUS PUBMED WOS cav_un_epca*0569631 Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - GRAPP SciTePress 2023 Lisbon 162 169 978-989-758-634-7 2184-4321 Sousa A. Augusto 340 Bashford-Rogers Thomas 340 Bouatouch Kadi 340