Allure of Craquelure: A Variational-Generative Approach to Crack Detection in Paintings
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917263847718912 |
|---|---|
| author | Paul, Laura Rauhut, Holger Burger, Martin Kabri, Samira Roith, Tim |
| author_facet | Paul, Laura Rauhut, Holger Burger, Martin Kabri, Samira Roith, Tim |
| contents | Recent advances in imaging technologies, deep learning and numerical performance have enabled non-invasive detailed analysis of artworks, supporting their documentation and conservation. In particular, automated detection of craquelure in digitized paintings is crucial for assessing degradation and guiding restoration, yet remains challenging due to the possibly complex scenery and the visual similarity between cracks and crack-like artistic features such as brush strokes or hair. We propose a hybrid approach that models crack detection as an inverse problem, decomposing an observed image into a crack-free painting and a crack component. A deep generative model is employed as powerful prior for the underlying artwork, while crack structures are captured using a Mumford--Shah-type variational functional together with a crack prior. Joint optimization yields a pixel-level map of crack localizations in the painting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_09730 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Allure of Craquelure: A Variational-Generative Approach to Crack Detection in Paintings Paul, Laura Rauhut, Holger Burger, Martin Kabri, Samira Roith, Tim Computer Vision and Pattern Recognition Machine Learning Numerical Analysis 68T10 (Primary), 68T07 (Secondary) I.5.0; J.5 Recent advances in imaging technologies, deep learning and numerical performance have enabled non-invasive detailed analysis of artworks, supporting their documentation and conservation. In particular, automated detection of craquelure in digitized paintings is crucial for assessing degradation and guiding restoration, yet remains challenging due to the possibly complex scenery and the visual similarity between cracks and crack-like artistic features such as brush strokes or hair. We propose a hybrid approach that models crack detection as an inverse problem, decomposing an observed image into a crack-free painting and a crack component. A deep generative model is employed as powerful prior for the underlying artwork, while crack structures are captured using a Mumford--Shah-type variational functional together with a crack prior. Joint optimization yields a pixel-level map of crack localizations in the painting. |
| title | Allure of Craquelure: A Variational-Generative Approach to Crack Detection in Paintings |
| topic | Computer Vision and Pattern Recognition Machine Learning Numerical Analysis 68T10 (Primary), 68T07 (Secondary) I.5.0; J.5 |
| url | https://arxiv.org/abs/2602.09730 |