0643909 20260224172604.420260105235959.9 10 s. E cav_un_epca*06439041613-0073GermanyCEUR-WS2025UrbanPhilippvon CastellChristoph FreiherrHardebergJon YngveFlemingRoland W.GigilashviliDavit Deep Learning Computer Graphics Rendering cav_un_auth*0500293 Amanturdieva A. NO 50 K cav_un_auth*0500294 Gigilashvili D. NO 25 cav_un_auth*0101086 Filip Jiří UTIA-B Rozpoznávání obrazu Department of Pattern Recognition RO RO Department of Pattern Recognition 25 Ústav teorie informace a automatizace AV ČR, v. v. i. PDF 4 MB https://library.utia.cas.cz/separaty/2026/RO/filip-0643909.pdf GA22-17529S GA ČR CZ cav_un_auth*0439849 This study explores the development of a deep learning-based predictive rendering system for 3D printed objects, addressing the challenge of accurately predicting surface appearance from input parameters like surface normals, light angles, view positions, and tangent vectors. By utilizing the Deep Shading architecture, we present and explore a method that synthesizes rendered appearances. The dataset, sourced from controlled multi-view and illumination imaging conditions, serves as the foundation for training and evaluating the model. We tested various loss functions and training data demonstrating a promising performance in 3D printed appearance reproduction. Our findings contribute to the broader effort of improving predictive rendering systems for 3D printed objects, with potential applications in manufacturing, design, and material science. cav_un_auth*0500280 MANER 2025 20250629 20250629 Mainz/Darmstadt DE IN 20000 20200 20201 2026 3 PR RVO:67985556 https://hdl.handle.net/11104/0374429 cav_un_auth*0402682 Norges teknisk-naturvitenskapelige universitet, Trondheim NTNU NO S 6 2025 SCOPUS PUBMED WOS cav_un_epca*0643904 Proceedings of the MANER Conference Mainz/Darmstadt 2025 (MANER 2025) 1613-0073 Germany CEUR-WS 2025 Vol-4135 CEUR Workshop Proceedings 4135 Urban Philipp 340 von Castell Christoph Freiherr 340 Hardeberg Jon Yngve 340 Fleming Roland W. 340 Gigilashvili Davit 340