11 citations · 28 across the 12 of their papers we have counts for
3 papers · 1 filter
RobustSAM: Segment Anything Robustly on Degraded Images
Wei-Ting Chen, Yu-Jiet Vong, Sy-Yen Kuo +2
Segment Anything Model (SAM) has emerged as a transformative approach in image segmentation, acclaimed for its robust zero-shot segmentation capabilities and flexible prompting sys…
DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformer
Wei-Ting Chen, Gurunandan Krishnan, Qiang Gao +3
Generic Face Image Quality Assessment (GFIQA) evaluates the perceptual quality of facial images, which is crucial in improving image restoration algorithms and selecting high-quali…
Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance
I-Hsiang Chen, Wei-Ting Chen, Yu-Wei Liu +2
Crowd counting and localization have become increasingly important in computer vision due to their wide-ranging applications. While point-based strategies have been widely used in…