4 papers
Eye image segmentation using visual and concept prompts with Segment Anything Model 3 (SAM3)
Diederick C. Niehorster, Marcus Nyström
Previous work has reported that vision foundation models show promising zero-shot performance in eye image segmentation. Here we examine whether the latest iteration of the Segment…
Zero-Shot Pupil Segmentation with SAM 2: A Case Study of Over 14 Million Images
Virmarie Maquiling, Sean Anthony Byrne, Diederick C. Niehorster +2
We explore the transformative potential of SAM 2, a vision foundation model, in advancing gaze estimation and eye tracking technologies. By significantly reducing annotation time,…
Zero-Shot Segmentation of Eye Features Using the Segment Anything Model (SAM)
Virmarie Maquiling, Sean Anthony Byrne, Diederick C. Niehorster +2
The advent of foundation models signals a new era in artificial intelligence. The Segment Anything Model (SAM) is the first foundation model for image segmentation. In this study,…
LEyes: A Lightweight Framework for Deep Learning-Based Eye Tracking using Synthetic Eye Images
Sean Anthony Byrne, Virmarie Maquiling, Marcus Nyström +2
Deep learning has bolstered gaze estimation techniques, but real-world deployment has been impeded by inadequate training datasets. This problem is exacerbated by both hardware-ind…