5 papers
CoRe-SAM3: Conditional Semantic--Visual Reconciliation for SAM3 Crack Segmentation
Shipeng Liu, Liang Zhao, Dengfeng Chen
Crack segmentation requires a model to recognize target semantics while accurately recovering thin, low-contrast, and topologically continuous local structures. Although SAM3 provi…
Rapid-Deployment Crack Measurement Based on SAM3 Semantic-Edge Response Decoding
Zhanping Song, Shipeng Liu, Liang Zhao +1
Reliable crack measurement is essential for infrastructure condition assessment, yet existing image-based approaches typically depend on pixel-wise annotations, task-specific segme…
Training-Free Tunnel Defect Inspection and Engineering Interpretation via Visual Recalibration and Entity Reconstruction
Shipeng Liu, Liang Zhao, Dengfeng Chen +1
Tunnel inspection requires outputs that can support defect localization, measurement, severity grading, and engineering documentation. Existing training-free foundation-model pipel…
Describe-to-Score: A text-guided framework for image complexity assessment
Shipeng Liu, Liang Zhao, Dengfeng Chen +1
Accurately assessing image complexity (IC) is essential for many vision tasks, yet existing approaches rely almost exclusively on visual features and therefore fail to capture the…
Contrastive Learning for Image Complexity Representation
Shipeng Liu, Liang Zhao, Dengfeng Chen +1
Quantifying and evaluating image complexity can be instrumental in enhancing the performance of various computer vision tasks. Supervised learning can effectively learn image compl…