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.

翻译：近年来，成像技术、深度学习与数值计算性能的进步，使得对艺术品的非侵入式精细分析成为可能，为其文献记录与保护提供了支持。其中，在数字化绘画中自动检测裂纹对于评估劣化程度及指导修复至关重要，但由于场景可能错综复杂，且裂纹与笔触、毛发等类似裂纹的艺术特征在视觉上相似，任务仍具挑战性。我们提出一种混合方法，将裂纹检测建模为逆问题，将观测图像分解为无裂纹绘画与裂纹分量。该方法采用深度生成模型作为内在艺术品的强先验，同时利用Mumford-Shah型变分泛函结合裂纹先验来捕捉裂纹结构。联合优化最终生成绘画中裂纹定位的像素级映射图。