Standard

Multi-scale convolutional neural network for pixel-wise reconstruction of Van Gogh’s drawings. / Zeng, Y.; van der Lubbe, J. C.A.; Loog, M.

In: Machine Vision and Applications, Vol. 30, No. 7-8, 01.10.2019, p. 1229-1241.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

APA

Vancouver

Author

Zeng, Y. ; van der Lubbe, J. C.A. ; Loog, M. / Multi-scale convolutional neural network for pixel-wise reconstruction of Van Gogh’s drawings. In: Machine Vision and Applications. 2019 ; Vol. 30, No. 7-8. pp. 1229-1241.

BibTeX

@article{c73af11958dd459daa383303253df821,
title = "Multi-scale convolutional neural network for pixel-wise reconstruction of Van Gogh{\textquoteright}s drawings",
abstract = "This paper investigates the reconstruction of Van Gogh{\textquoteright}s drawings which have been degraded in the course of time due to aging problems, like ink fading and discoloration. Learning to predict the past and original appearances of degraded drawings can help to envisage how the artist{\textquoteright}s work may have looked at the time of creation. In this paper, we use reproductions as reference information for the past appearances of drawings and consider the reconstruction of drawings as a pixel-wise prediction problem. We present an approach to automatically predict the past appearances of drawings. This approach brings together methods from multi-resolution image analysis and deep convolutional neural networks (CNNs) for addressing the task of pixel-wise prediction. Our experiments first investigate how scale affects prediction performance of the proposed multi-scale CNN framework and then demonstrate the reconstruction capability of the multi-scale CNN framework. The results demonstrate that the predictive reconstruction of degraded images is a feasible endeavor.",
keywords = "Convolutional neural networks, Image reconstruction, Pixel-wise prediction, Van Gogh{\textquoteright}s drawings",
author = "Y. Zeng and {van der Lubbe}, {J. C.A.} and M. Loog",
year = "2019",
month = oct,
day = "1",
doi = "10.1007/s00138-019-01047-3",
language = "English",
volume = "30",
pages = "1229--1241",
journal = "Machine Vision & Applications: an international journal",
issn = "0932-8092",
publisher = "Springer",
number = "7-8",

}

RIS

TY - JOUR

T1 - Multi-scale convolutional neural network for pixel-wise reconstruction of Van Gogh’s drawings

AU - Zeng, Y.

AU - van der Lubbe, J. C.A.

AU - Loog, M.

PY - 2019/10/1

Y1 - 2019/10/1

N2 - This paper investigates the reconstruction of Van Gogh’s drawings which have been degraded in the course of time due to aging problems, like ink fading and discoloration. Learning to predict the past and original appearances of degraded drawings can help to envisage how the artist’s work may have looked at the time of creation. In this paper, we use reproductions as reference information for the past appearances of drawings and consider the reconstruction of drawings as a pixel-wise prediction problem. We present an approach to automatically predict the past appearances of drawings. This approach brings together methods from multi-resolution image analysis and deep convolutional neural networks (CNNs) for addressing the task of pixel-wise prediction. Our experiments first investigate how scale affects prediction performance of the proposed multi-scale CNN framework and then demonstrate the reconstruction capability of the multi-scale CNN framework. The results demonstrate that the predictive reconstruction of degraded images is a feasible endeavor.

AB - This paper investigates the reconstruction of Van Gogh’s drawings which have been degraded in the course of time due to aging problems, like ink fading and discoloration. Learning to predict the past and original appearances of degraded drawings can help to envisage how the artist’s work may have looked at the time of creation. In this paper, we use reproductions as reference information for the past appearances of drawings and consider the reconstruction of drawings as a pixel-wise prediction problem. We present an approach to automatically predict the past appearances of drawings. This approach brings together methods from multi-resolution image analysis and deep convolutional neural networks (CNNs) for addressing the task of pixel-wise prediction. Our experiments first investigate how scale affects prediction performance of the proposed multi-scale CNN framework and then demonstrate the reconstruction capability of the multi-scale CNN framework. The results demonstrate that the predictive reconstruction of degraded images is a feasible endeavor.

KW - Convolutional neural networks

KW - Image reconstruction

KW - Pixel-wise prediction

KW - Van Gogh’s drawings

UR - http://www.scopus.com/inward/record.url?scp=85074213866&partnerID=8YFLogxK

U2 - 10.1007/s00138-019-01047-3

DO - 10.1007/s00138-019-01047-3

M3 - Article

AN - SCOPUS:85074213866

VL - 30

SP - 1229

EP - 1241

JO - Machine Vision & Applications: an international journal

JF - Machine Vision & Applications: an international journal

SN - 0932-8092

IS - 7-8

ER -

ID: 66574414