Neural Acceleration of Scattering-Aware Color 3D Printing

Rittig T, Sumin D, Babaei V, Didyk P, Voloboy A, Wilkie A, Bickel B, Myszkowski K, Weyrich T, Krivanek J (2021)

Publication Type: Journal article

Publication year: 2021

Journal

Computer Graphics Forum Wiley-Blackwell

Book Volume: 40

Pages Range: 205-219

Journal Issue: 2

DOI: 10.1111/cgf.142626

Abstract

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.

Authors with CRIS profile

Tim Weyrich

Involved external institutions

Univerzita Karlova v Praze / Charles University in Prague CZ Czech Republic (CZ) Max Planck Institute for Informatics / Max-Planck-Institut für Informatik DE Germany (DE) Università della Svizzera italiana (USI) CH Switzerland (CH) Keldysh Institute of Applied Mathematics / Федеральное государственное учреждение "Федеральный исследовательский центр Институт прикладной математики им. М.В. Келдыша Российской академии наук" / ИПМ им. М.В. Келдыша РА RU Russian Federation (RU) IST Austria AT Austria (AT) University College London (UCL) GB United Kingdom (GB)

How to cite

APA:

Rittig, T., Sumin, D., Babaei, V., Didyk, P., Voloboy, A., Wilkie, A.,... Krivanek, J. (2021). Neural Acceleration of Scattering-Aware Color 3D Printing. Computer Graphics Forum, 40(2), 205-219. https://dx.doi.org/10.1111/cgf.142626

MLA:

Rittig, Tobias, et al. "Neural Acceleration of Scattering-Aware Color 3D Printing." Computer Graphics Forum 40.2 (2021): 205-219.

BibTeX: Download