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

Laura Paul; Holger Rauhut; Martin Burger; Samira Kabri; Tim Roith

cs.CVFeb 10, 2026

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

Authors: Laura Paul, Holger Rauhut, Martin Burger, Samira Kabri, Tim Roith

Organizations: Dept. of Mathematics, LMU Munich, Germany · Munich Center for Machine Learning, Germany · Helmholtz Imaging, Deutsches Elektronen-Synchrotron DESY, Germany · Fachbereich Mathematik, University of Hamburg, Germany · CIT School, Technical University of Munich,Germany

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.

Explore similar work

An End-to-End Automated Pipeline for Controllable Crack Data Synthesis
Sep 11, 2026Conghui Li, Muxin Pu, Chern Hong Lim +2Inpainting Augmentation
CrackForward: Context-Aware Severity Stage Crack Synthesis for Data Augmentation
Apr 21, 2026Nassim Sadallah, Mohand Saïd AlliliSynthetic Data Augmentation Generative Adversarial Network
Compass: Degradation-Simulated Reciprocal Learning with Lightweight Needle RWKV for Multimodal Crack Segmentation under Missing Modalities
Aug 4, 2026Hui Liu, Chen Jia, Fan Shi +3Missing Modalities Multimodal Learning

Sep 11, 2026 · cs.CVJ/K move · Enter open · S save

An End-to-End Automated Pipeline for Controllable Crack Data Synthesis

Conghui Li, Muxin Pu, Chern Hong Lim, Weiyao Lin+1

School of Information Technology, Monash University, Selangor, Malaysia · Department of Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China · School of Engineering, Monash University, Selangor, Malaysia

Vision-based crack inspection depends on segmentation networks whose reliability depends on the quantity, diversity and label quality of their training data. Pixel-level annotations are costly, and crack images of specific structures are scarce. Generative augmentation can supply additional data, but existing methods address isolated steps. They reuse annotated masks, offer limited control over crack geometry, and adopt the conditioning mask as the label without checking it. This paper presents an end-to-end pipeline that produces labelled crack data without manual annotation and assesses the reliability of these data and of the detectors trained on them. Procedurally sampled Bézier skeletons with guaranteed geometric properties are converted into crack masks by a generative adversarial network (GAN). A dual-ControlNet Stable Diffusion model renders the masks as crack images, either on text-described surfaces or on user-provided backgrounds. An ensemble of segmentation networks trained on real images combines its agreement with the inherited label and its internal disagreement into a pixel-wise label confidence. This confidence weights the training loss instead of removing samples with a threshold. The trained detectors are evaluated with image-space probability of detection (POD) and calibration analyses. On CRACK500 and CrackTree200, the pipeline improves five segmentation networks over conventional, diffusion-based and flow-matching-based augmentation, and on CRACK500 confidence weighting yields a higher accuracy than threshold filtering at every tested threshold. On CRACK500, the crack width that U-Net detects with 90% probability at 95% confidence decreases from 8.0 to 4.3 pixels, and the expected calibration error decreases from 14.2% to 9.6%.

Inpainting Augmentation Automated Synthesis Techniques

Open paper Ask about it PDF

Abstract

Explore similar work

An End-to-End Automated Pipeline for Controllable Crack Data Synthesis

CrackForward: Context-Aware Severity Stage Crack Synthesis for Data Augmentation

Compass: Degradation-Simulated Reciprocal Learning with Lightweight Needle RWKV for Multimodal Crack Segmentation under Missing Modalities