Al-Sameai, HabebSaleh, Radhwan A.A.Moura, Joaquim deAkay, Rustu2026-07-242026-07-242026H. Al-Sameai, R. A.A. Saleh, J. de Moura, and R. Akay, "Dual-encoder Multi-Scale Refinement Network for Robust Crack Segmentation Across Diverse Domains", Automation in Construction, vol. 188, 107004. https://doi.org/10.1016/j.autcon.2026.1070040926-5805https://hdl.handle.net/2183/48930The code and links to the datasets supporting the findings of this study are available at https://github.com/habeeb96/DMSRCrack.[Abstract]: Accurate crack segmentation is critical for infrastructure monitoring but remains challenging due to diverse crack morphologies, complex backgrounds, and domain shifts. This paper proposes DMSRCrack, a Dual-encoder Multi-Scale Refinement network for robust crack segmentation across diverse domains. The proposed architecture integrates a hybrid CNN–ViT encoder for local and global feature extraction, a Crack Detail Enhancement Module (CDEM) for preserving thin crack structures, a Boundary Refinement Head (BRH) for contour sharpening, and a Multi-Scale Fusion (MSF) module for scale-consistent representation. Across eight benchmark datasets, DMSRCrack achieves an average Dice of 0.7949 ± 0.0655 and IoU of 0.6639 ± 0.0917 in dataset-wise training. Under leave-one-dataset-out evaluation, it attains the highest IoU on DeepCrack (0.4056), Rissbilder (0.3540), and Crack500 (0.3008). Ablation and computational analyses further confirm the effectiveness and practical efficiency of the proposed contributions.engAttribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/Crack segmentationDeep learningCNN–ViT hybridMulti-scale feature fusionBoundary refinementGeneralization performanceInfrastructure monitoringjournal articleopen access10.1016/j.autcon.2026.107004