Next Article in Journal
Identification of IoT Actors
Previous Article in Journal
Fast Quantification of Air Pollutants by Mid-Infrared Hyperspectral Imaging and Principal Component Analysis
Previous Article in Special Issue
Protocol Development for Point Clouds, Triangulated Meshes and Parametric Model Acquisition and Integration in an HBIM Workflow for Change Control and Management in a UNESCO’s World Heritage Site
Article

Colour-Balanced Edge-Guided Digital Inpainting: Applications on Artworks

Department of Computer Science, NTNU—Norwegian University of Science and Technology, 2815 Gjøvik, Norway
*
Author to whom correspondence should be addressed.
Academic Editors: Anastasios Doulamis and Eui Chul Lee
Sensors 2021, 21(6), 2091; https://doi.org/10.3390/s21062091
Received: 30 December 2020 / Revised: 10 March 2021 / Accepted: 11 March 2021 / Published: 17 March 2021
(This article belongs to the Special Issue Smart Sensors Data Processing and Visualization in Cultural Heritage)
The virtual inpainting of artworks provides a nondestructive mode of hypothesis visualization, and it is especially attractive when physical restoration raises too many methodological and ethical concerns. At the same time, in Cultural Heritage applications, the level of details in virtual reconstruction and their accuracy are crucial. We propose an inpainting algorithm that is based on generative adversarial network, with two generators: one for edges and another one for colors. The color generator rebalances chromatically the result by enforcing a loss in the discretized gamut space of the dataset. This way, our method follows the modus operandi of an artist: edges first, then color palette, and, at last, color tones. Moreover, we simulate the stochasticity of the lacunae in artworks with morphological variations of a random walk mask that recreate various degradations, including craquelure. We showcase the performance of our model on a dataset of digital images of wall paintings from the Dunhuang UNESCO heritage site. Our proposals of restored images are visually satisfactory and they are quantitatively comparable to state-of-the-art approaches. View Full-Text
Keywords: inpainting; colorization; generative adversarial networks; dunhuang wall paintings inpainting; colorization; generative adversarial networks; dunhuang wall paintings
Show Figures

Figure 1

MDPI and ACS Style

Ciortan, I.-M.; George, S.; Hardeberg, J.Y. Colour-Balanced Edge-Guided Digital Inpainting: Applications on Artworks. Sensors 2021, 21, 2091. https://doi.org/10.3390/s21062091

AMA Style

Ciortan I-M, George S, Hardeberg JY. Colour-Balanced Edge-Guided Digital Inpainting: Applications on Artworks. Sensors. 2021; 21(6):2091. https://doi.org/10.3390/s21062091

Chicago/Turabian Style

Ciortan, Irina-Mihaela, Sony George, and Jon Y. Hardeberg 2021. "Colour-Balanced Edge-Guided Digital Inpainting: Applications on Artworks" Sensors 21, no. 6: 2091. https://doi.org/10.3390/s21062091

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop