activity
20242026
collaborators

5 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…

cs.CV2024

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…