Neural Acceleration of Scattering-Aware Color 3D Printing
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10432209" target="_blank" >RIV/00216208:11320/21:10432209 - isvavai.cz</a>
Result on the web
<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=vJDO8XglZp" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=vJDO8XglZp</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1111/cgf.142626" target="_blank" >10.1111/cgf.142626</a>
Alternative languages
Result language
angličtina
Original language name
Neural Acceleration of Scattering-Aware Color 3D Printing
Original language description
With the wider availability of full-color 3D printers, color-accurate 3D-print preparation has received increased attention. A key challenge lies in the inherent translucency of commonly used print materials that blurs out details of the color texture. Previous work tries to compensate for these scattering effects through strategic assignment of colored primary materials to printer voxels. To date, the highest-quality approach uses iterative optimization that relies on computationally expensive Monte Carlo light transport simulation to predict the surface appearance from subsurface scattering within a given print material distribution; that optimization, however, takes in the order of days on a single machine. In our work, we dramatically speed up the process by replacing the light transport simulation with a data-driven approach. Leveraging a deep neural network to predict the scattering within a highly heterogeneous medium, our method performs around two orders of magnitude faster than Monte Carlo rendering while yielding optimization results of similar quality level. The network is based on an established method from atmospheric cloud rendering, adapted to our domain and extended by a physically motivated weight sharing scheme that substantially reduces the network size. We analyze its performance in an end-to-end print preparation pipeline and compare quality and runtime to alternative approaches, and demonstrate its generalization to unseen geometry and material values. This for the first time enables full heterogenous material optimization for 3D-print preparation within time frames in the order of the actual printing time.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/GA19-07626S" target="_blank" >GA19-07626S: High-fidelity appearance fabrication</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Computer Graphics Forum
ISSN
0167-7055
e-ISSN
—
Volume of the periodical
40
Issue of the periodical within the volume
2
Country of publishing house
GB - UNITED KINGDOM
Number of pages
15
Pages from-to
205-219
UT code for WoS article
000657959600017
EID of the result in the Scopus database
2-s2.0-85107349912