A Multi-Resolution Attention U-Net for Pavement Distress Segmentation in 3D Images: Architecture and Data-Driven Insights

High-resolution 3D pavement images have become a valuable data source for automated surface distress detection and assessment. However, accurately identifying and segmenting cracks from pavement images remains challenging, due to factors such as low contrast and hair-like thinness. This study investigates key factors affecting segmentation performance and proposes a novel deep learning architecture designed to enhance segmentation robustness under these challenging conditions. The proposed model integrates a multi-resolution feature extraction stream with gated attention mechanisms to improve spatial awareness and selectively fuse information across feature levels. Our extensive experiments on a 3D pavement dataset demonstrated that the proposed method outperformed several state-of-the-art architectures, including FCN, U-Net, DeepLab, DeepCrack, and CrackFormer. Compared with U-Net, it improved F1 from 0.733 to 0.780. The gains were most pronounced on thin cracks, with F1 from 0.531 to 0.626. Our paired t-tests across folds showed the method is statistically better than U-Net and DeepCrack on Recall, IoU, Dice, and F1. These findings highlight the effectiveness of the attention-guided, multi-scale feature fusion method for robust crack segmentation using 3D pavement data.