5 papers
Registration-Grounded Spectral Fusion for Unregistered WLI/NBI Endoscopic Lesion Segmentation
Pengyu Jie, Wanquan Liu, Rui He +5
White-light imaging (WLI) and narrow-band imaging (NBI) provide complementary views of endoscopic lesions, but their paired observations are often spatially misaligned due to viewp…
SOFTooth: Semantics-Enhanced Order-Aware Fusion for Tooth Instance Segmentation
Xiaolan Li, Wanquan Liu, Pengcheng Li +2
Three-dimensional (3D) tooth instance segmentation remains challenging due to crowded arches, ambiguous tooth-gingiva boundaries, missing teeth, and rare yet clinically important t…
Diffusion-Guided Mask-Consistent Paired Mixing for Endoscopic Image Segmentation
Pengyu Jie, Wanquan Liu, Rui He +3
Augmentation for dense prediction typically relies on either sample mixing or generative synthesis. Mixing improves robustness but misaligned masks yield soft label ambiguity. Diff…
AFR-CLIP: Enhancing Zero-Shot Industrial Anomaly Detection with Stateless-to-Stateful Anomaly Feature Rectification
Jingyi Yuan, Chenqiang Gao, Pengyu Jie +3
Recently, zero-shot anomaly detection (ZSAD) has emerged as a pivotal paradigm for industrial inspection and medical diagnostics, detecting defects in novel objects without requiri…
A Point-Neighborhood Learning Framework for Nasal Endoscope Image Segmentation
Pengyu Jie, Wanquan Liu, Chenqiang Gao +6
Lesion segmentation on nasal endoscopic images is challenging due to its complex lesion features. Fully-supervised deep learning methods achieve promising performance with pixel-le…