Computer-Aided reclamation of lost art

Authors:
Maria Lena Demetriou;Jon Yngve Hardeberg;Gabriel Adelmann
Affiliations:
The Norwegian Colour and Visual Computing Laboratory, Gjøvik University College, Gjøvik, Norway;The Norwegian Colour and Visual Computing Laboratory, Gjøvik University College, Gjøvik, Norway;The Norwegian Colour and Visual Computing Laboratory, Gjøvik University College, Gjøvik, Norway
Venue:
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part I
Year:
2012

Citing 12
Cited 0

Learning Low-Level Vision

International Journal of Computer Vision - Special issue on statistical and computational theories of vision: modeling, learning, sampling and computing, Part I
Color Transfer between Images

IEEE Computer Graphics and Applications
Example-Based Super-Resolution

IEEE Computer Graphics and Applications
Recognising Panoramas

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Color transfer in correlated color space

Proceedings of the 2006 ACM international conference on Virtual reality continuum and its applications
Image Denoising Via Learned Dictionaries and Sparse representation

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
On single image scale-up using sparse-representations

Proceedings of the 7th international conference on Curves and Surfaces
-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation

IEEE Transactions on Signal Processing
Image quality assessment: from error visibility to structural similarity

IEEE Transactions on Image Processing
Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries

IEEE Transactions on Image Processing
Inverse halftoning and kernel estimation for error diffusion

IEEE Transactions on Image Processing
Histogram-Based Prefiltering for Luminance and Chrominance Compensation of Multiview Video

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

There are numerous approaches towards restoration of art, including computer applications as aid to manual performance. However, to our knowledge, it has not been attempted to recuperate high quality images of missing or presumably destroyed works of art. While these works will never again be available in their original form, it may be feasible to considerably enhance the quality of preserved photographic reproductions. A pioneering combination of super-resolution and colour correction is presented here, targeting the reclamation of high quality images of lost works of art. The techniques are performed by example, utilising correspondence between artworks of similar nature, currently available both in low and high quality. With extensive prior knowledge in the domains of super-resolution and colour correction, selected approaches were studied, implemented and tested, concluding to the most efficient. Experimental results are highly promising, revealing a new research path in colour imaging for fine art.