龟裂的魅力：一种变分-生成式绘画裂纹检测方法
Allure of Craquelure: A Variational-Generative Approach to Crack Detection in Paintings
AI总结：
提出混合方法，将裂纹检测建模为逆问题，用深度生成模型作为画作先验，结合Mumford-Shah变分泛函和裂纹先验，通过联合优化获得像素级裂纹定位图。
摘要：
近期成像技术、深度学习与数值性能的进步使得对艺术品的非侵入性详细分析成为可能，支持其记录与保护。特别是，数字化绘画中龟裂的自动检测对于评估退化和指导修复至关重要，但由于可能复杂的场景以及裂纹与类似裂纹的艺术特征（如笔触或毛发）之间的视觉相似性，这仍然具有挑战性。我们提出一种混合方法，将裂纹检测建模为一个逆问题，将观测图像分解为无裂纹绘画和裂纹分量。采用深度生成模型作为底层艺术品的有力先验，同时使用Mumford-Shah型变分泛函结合裂纹先验来捕捉裂纹结构。联合优化得到绘画中裂纹定位的像素级图。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
