Computer Graphics Laboratory ETH Zurich

ETH

Advanced tools and framework for historical film restoration

S. Croci, T. O. Aydin, S. Nikolce, M. Gross, A. Smolic

Journal of Electronic Imaging, SPIE and IS&T, vol. 26, no. 1, 2017, pp. 011021
[Abstract] [BibTeX] [PDF]

Abstract

Digital restoration of film content that has historical value is crucial for the preservation of cultural heritage. Also, digital restoration is not only a relevant application area of various video processing technologies that have been developed in computer graphics literature but also involves a multitude of unresolved research challenges. Currently, the digital restoration workflow is highly labor intensive and often heavily relies on expert knowledge. We revisit some key steps of this workflow and propose semiautomatic methods for performing them. To do that we build upon state-of-the-art video processing techniques by adding the components necessary for enabling (i) restoration of chemically degraded colors of the film stock, (ii) removal of excessive film grain through spatiotemporal filtering, and (iii) contrast recovery by transferring contrast from the negative film stock to the positive. We show that when applied individually our tools produce compelling results and when applied in concert significantly improve the degraded input content. Building on a conceptual framework of film restoration ensures the best possible combination of tools and use of available materials.

@article{doi:10.1117/1.JEI.26.1.011021,
author = {Croci, Simone and Aydın, Tunç Ozan and Stefanoski, Nikolce and Gross, Markus and Smolic, Aljosa},
title = {Advanced tools and framework for historical film restoration},
journal = {Journal of Electronic Imaging},
volume = {26},
number = {1},
pages = {011021},
abstract = {Digital restoration of film content that has historical value is crucial for the preservation of cultural heritage. Also, digital restoration is not only a relevant application area of various video processing technologies that have been developed in computer graphics literature but also involves a multitude of unresolved research challenges. Currently, the digital restoration workflow is highly labor intensive and often heavily relies on expert knowledge. We revisit some key steps of this workflow and propose semiautomatic methods for performing them. To do that we build upon state-of-the-art video processing techniques by adding the components necessary for enabling (i) restoration of chemically degraded colors of the film stock, (ii) removal of excessive film grain through spatiotemporal filtering, and (iii) contrast recovery by transferring contrast from the negative film stock to the positive. We show that when applied individually our tools produce compelling results and when applied in concert significantly improve the degraded input content. Building on a conceptual framework of film restoration ensures the best possible combination of tools and use of available materials.},
year = {2017},
isbn = {1017-9909},
doi = {10.1117/1.JEI.26.1.011021},
URL = { http://dx.doi.org/10.1117/1.JEI.26.1.011021},
eprint = {}
}
[Download BibTeX]

Downloads

Download Paper
[PDF]