Training-Free Semantic-Edge Response Decoding of SAM3 for Cross-Domain Infrastructure Crack Segmentation

Cross-project crack segmentation is hindered by variations in materials, imaging conditions, crack morphology, and background interference. Text-promptable foundation models reduce task-specific training, but SAM3’s final region proposals may suppress, truncate, or distort weak and fragmented cracks. We propose $\mathbf{\text{S}}$emantic-$\mathbf{\text{E}}$dge $\mathbf{\text{R}}$esponse $\mathbf{\text{D}}$ecoding ($\mathbf{\text{SERD}}$), a training-free method that replaces the proposal interface with the internal language-conditioned response. SERD normalizes this dense response, calibrates it using a fixed Sobel structural prior, and applies a single threshold to generate the crack mask. SAM3 remains frozen, with no target-domain annotation, auxiliary prompting network, or test-time optimization. When CamCrack789 is used only for threshold selection, SERD achieves 58.00% average Crack IoU on five unseen datasets, compared with 54.33% for native SAM3. Across six rotated source-domain settings, SERD obtains 60.23% mean target-domain IoU and 67.18% Boundary F1, exceeding SAM3 by 3.27 and 2.70 percentage points. Regional, structural, foreground-area, robustness, and latency analyses show that direct response decoding recovers substantial crack evidence lost during proposal formation, while structural calibration improves precision and boundary localization. The results demonstrate that internal-response decoding provides a simple and transferable interface for cross-domain infrastructure crack segmentation. $\mathit{\text{Code}}\mathit{\text{is}}\mathit{\text{available}}\mathit{\text{at:}}\mathit{\text{href}}$.