Allure of Craquelure: A Variational-Generative Approach to Crack Detection in Paintings

2026-02-10

AI Summary

This work addresses the challenge of accurately detecting craquelure in paintings, where visual similarities between cracks and artistic features such as brushstrokes or hair often lead to false positives. To resolve this ambiguity, the authors propose a hybrid inverse problem framework that integrates deep generative priors with a Mumford–Shah-type variational functional, decomposing an input image into a crack-free painting component and a crack-specific layer. By employing a joint optimization strategy, the method uniquely combines the expressive power of generative models with crack-tailored regularization, enabling pixel-level crack localization. Evaluated on complex artistic scenes, the approach significantly enhances the ability to distinguish genuine craquelure from crack-like textures, achieving high-precision detection performance.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

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.

Problem

• craquelure
• crack detection
• painting restoration
• artwork conservation
• image decomposition

Innovation

• craquelure detection
• variational-generative model
• inverse problem
• Mumford-Shah functional
• deep generative prior