Bart Devolder
Princeton University
8 Papers
10 Citations
Bart Devolder is an academic researcher from Princeton University. The author has contributed to research in topics: Altarpiece & Inpainting. The author has an hindex of 2, co-authored 8 publications. Previous affiliations of Bart Devolder include Royal Institute for Cultural Heritage.
Chat about Author
Papers
Digital Image Processing of The Ghent Altarpiece: Supporting the painting's study and conservation treatment
Aleksandra Pizurica,Ljiljana Platisa,Tijana Ruzic,Bruno Cornelis,Ann Dooms,Maximiliaan Martens,Hélène Dubois,Bart Devolder,Marc De Mey,Ingrid Daubechies +9 more
TL;DR: Hanging in the Saint Bavo Cathedral in Ghent, Belgium, is The Ghent Altarpiece, also known as The Adoration of the Mystic Lamb, one of the most admired and influential paintings in the history of art.
Multimodal Target Detection by Sparse Coding: Application to Paint Loss Detection in Paintings
TL;DR: This paper proposes a sparsity-based multimodal target detection method that processes jointly the information from multiple imaging modalities in a kernel feature space, and making use of the spatial context, and develops the target detector such to be robust to errors in labelled data.
10
Deep Learning for Paint Loss Detection with a multiscale, translation invariant network
Laurens Meeus,Shaoguang Huang,Bart Devolder,Hélène Dubois,Maximiliaan Martens,Aleksandra Pizurica +5 more
- 01 Sep 2019
TL;DR: In this paper, a multiscale deep learning system with dilated convolutions is proposed to detect paint loss in digital paintings, which enables a large receptive field with limited training parameters to avoid overtraining.
10
Paint loss detection via kernel sparse representation
Shaoguang Huang,Laurens Meeus,Bruno Cornelis,Bart Devolder,Maximiliaan Martens,Aleksandra Pizurica +5 more
- 01 Jan 2018
TL;DR: A multimodal paint loss detection method based on sparse representation is developed, which incorporates the information from multiple imaging modalities in a high-dimensional kernel feature space and makes use of the spatial context to cope with unreliable labelled data.
2
Deep Learning for Paint Loss Detection: A Case Study on the Ghent Altarpiece
Laurens Meeus,Shaoguang Huang,Bart Devolder,Maximiliaan Martens,Aleksandra Pizurica +4 more
- 01 Jan 2018
TL;DR: A multiscale deep learning method is developed, based on the recent UNet architecture, which is applicable to multimodal acquisitions such as visible, infrared, x-ray, and ultraviolet fluorescence and extends with dilated convolutions, such as to improve the detection stability.
1