无需标注数据，用生成裂缝模拟修复画作裂纹。
Synthetic Craquelure Generation for Unsupervised Painting Restoration
- 用贝塞尔曲线生成逼真裂纹，结合形态学检测与低秩微调模型。
- 零样本下修复效果超越现有照片修复模型，保持原笔触细节。
- 适合艺术修复、数字文物保护领域研究者使用。
文化遗产保护日益需要无侵入性的数字修复方法，但因缺乏像素级标注，从复杂笔触中识别并修复细小裂纹仍具挑战。本文提出一种全无标注的框架，基于特定领域裂纹生成器，利用贝塞尔轨迹模拟真实的分支与渐细裂纹结构。方法结合经典形态学检测器与基于学习的精修模块：采用通过低秩适应（LoRA）微调的SegFormer骨干网络。独特之处在于采用检测引导策略，将形态学图作为空间先验输入，同时使用掩码混合损失和逻辑值调整，使训练聚焦于优化候选裂纹区域。精修后的掩码引导各向异性扩散修复阶段，重建缺失内容。实验表明，该流程在零样本设置下显著优于当前最优的摄影修复模型，同时忠实保留原始画笔痕迹。
原文摘要 · Abstract (English)
Cultural heritage preservation increasingly demands non-invasive digital methods for painting restoration, yet identifying and restoring fine craquelure patterns from complex brushstrokes remains challenging due to scarce pixel-level annotations. We propose a fully annotation-free framework driven by a domain-specific synthetic craquelure generator, which simulates realistic branching and tapered fissure geometry using Bézier trajectories. Our approach couples a classical morphological detector with a learning-based refinement module: a SegFormer backbone adapted via Low-Rank Adaptation (LoRA). Uniquely, we employ a detector-guided strategy, injecting the morphological map as an input spatial prior, while a masked hybrid loss and logit adjustment constrain the training to focus specifically on refining candidate crack regions. The refined masks subsequently guide an Anisotropic Diffusion inpainting stage to reconstruct missing content. Experimental results demonstrate that our pipeline significantly outperforms state-of-the-art photographic restoration models in zero-shot settings, while faithfully preserving the original paint brushwork.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。