bibtype C - Conference Paper (international conference)
ARLID 0643909
utime 20260115100306.4
mtime 20260105235959.9
title (primary) (eng) Deep learning for predictive rendering of 3D printed objects
specification
page_count 10 s.
media_type E
serial
ARLID cav_un_epca*0643904
ISSN 1613-0073
title Proceedings of the MANER Conference Mainz/Darmstadt 2025 (MANER 2025)
publisher
place Germany
name CEUR-WS
year 2025
editor
name1 Urban
name2 Philipp
editor
name1 von Castell
name2 Christoph Freiherr
editor
name1 Hardeberg
name2 Jon Yngve
editor
name1 Fleming
name2 Roland W.
editor
name1 Gigilashvili
name2 Davit
keyword Deep Learning
keyword Computer Graphics
keyword Rendering
author (primary)
ARLID cav_un_auth*0500293
name1 Amanturdieva
name2 A.
country NO
share 50
garant K
author
ARLID cav_un_auth*0500294
name1 Gigilashvili
name2 D.
country NO
share 25
author
ARLID cav_un_auth*0101086
name1 Filip
name2 Jiří
institution UTIA-B
full_dept (cz) Rozpoznávání obrazu
full_dept Department of Pattern Recognition
department (cz) RO
department RO
full_dept Department of Pattern Recognition
share 25
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
source
source_type PDF
source_size 4 MB
url https://library.utia.cas.cz/separaty/2026/RO/filip-0643909.pdf
cas_special
project
project_id GA22-17529S
agency GA ČR
country CZ
ARLID cav_un_auth*0439849
abstract (eng) 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.
action
ARLID cav_un_auth*0500280
name MANER 2025
dates 20250629
mrcbC20-s 20250629
place Mainz/Darmstadt
country DE
RIV IN
FORD0 20000
FORD1 20200
FORD2 20201
reportyear 2026
num_of_auth 3
presentation_type PR
inst_support RVO:67985556
permalink https://hdl.handle.net/11104/0374429
cooperation
ARLID cav_un_auth*0402682
name Norges teknisk-naturvitenskapelige universitet, Trondheim
institution NTNU
country NO
confidential S
article_num 6
arlyear 2025
mrcbU14 SCOPUS
mrcbU24 PUBMED
mrcbU34 WOS
mrcbU63 cav_un_epca*0643904 Proceedings of the MANER Conference Mainz/Darmstadt 2025 (MANER 2025) 1613-0073 0074-4135 Germany CEUR-WS 2025 Vol-4135 CEUR Workshop Proceedings 4135
mrcbU67 Urban Philipp 340
mrcbU67 von Castell Christoph Freiherr 340
mrcbU67 Hardeberg Jon Yngve 340
mrcbU67 Fleming Roland W. 340
mrcbU67 Gigilashvili Davit 340