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

Y. Zeng*, J. C.A. van der Lubbe, M. Loog

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

9 Citations (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)1229-1241
Number of pages13
JournalMachine Vision and Applications
Volume30
Issue number7-8
DOIs
Publication statusPublished - 1 Oct 2019

Keywords

  • Convolutional neural networks
  • Image reconstruction
  • Pixel-wise prediction
  • Van Gogh’s drawings

Fingerprint

Dive into the research topics of 'Multi-scale convolutional neural network for pixel-wise reconstruction of Van Gogh’s drawings'. Together they form a unique fingerprint.

Cite this