Repaint: Deep Multispectral Painting Reproduction via
Multi-Layer, Custom-Ink Printing

SIGGRAPH Asia 2018

Liang Shi1     Vahid Babaei1,2     Changil Kim1     Michael Foshey1     Yuanming Hu1    
Pitchaya Sitthi-amorn3     Szymon Rusinkiewicz4     Wojciech Matusik1    
1Massachusetts Institute of Technology      2MPI Informatik & Saarland University MMCI
3 Chulalongkorn University      4 Princeton University

Four patches of reproduced paintings on top of the originals. Our workflow uses 10 inks and AI to accurately reproduces the spectral reflectance so that the color matches under varying lightings. Paintings © Azadeh Asadi.


Abstract


We propose a workflow for spectral reproduction of paintings, which captures a painting’s spectral color, invariant to illumination, and reproduces it using multi-material 3D printing. We take advantage of the current 3D printers’ capabilities of combining highly concentrated inks with a large number of layers, to expand the spectral gamut of a set of inks. We use a data-driven method to both predict the spectrum of a printed ink stack and optimize for the stack layout that best matches a target spectrum. This bidirectional mapping is modeled using a pair of neural networks, which are optimized through a problem-specific multi-objective loss function. Our loss function helps find the best possible ink layout resulting in the balance between spectral reproduction and colorimetric accuracy under a multitude of illuminants. In addition, we introduce a novel spectral vector error diffusion algorithm based on combining color contoning and halftoning, which simultaneously solves the layout discretization and color quantization problems, accurately and efficiently. Our workflow outperforms the state-of-the-art models for spectral prediction and layout optimization. We demonstrate reproduction of a number of real paintings and historically important pigments using our prototype implementation that uses 10 custom inks with varying spectra and a resin-based 3D printer.


Paper


Repaint: Deep Multispectral Painting Reproduction via Multi-Layer, Custom-Ink Printing
Liang Shi, Vahid Babaei, Changil Kim, Michael Foshey, Yuanming Hu, Pitchaya Sitthi-amorn, Szymon Rusinkiewicz, Wojciech Matusik
ACM Transactions on Graphics 37(6) (Proc. SIGGRAPH Asia 2018)
[Paper]  [Supp]  [Multispectral Scans (1.4G)]  [Ink Dataset (3.6M)]  [BibTeX]


Video


Fast Forward


MIT News Video




Press