Výsledky vyhledávání - "Byrne, Sean Anthony"

Report

Zero-Shot Pupil Segmentation with SAM 2: A Case Study of Over 14 Million Images

Autor: Maquiling, Virmarie, Byrne, Sean Anthony, Niehorster, Diederick C., Carminati, Marco, Kasneci, Enkelejda

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, lowering technical barriers through its ease of deployment, and enhanc

Externí odkaz: http://arxiv.org/abs/2410.08926

Zobrazit plný text záznamu

Report

Zero-Shot Segmentation of Eye Features Using the Segment Anything Model (SAM)

Autor: Maquiling, Virmarie, Byrne, Sean Anthony, Niehorster, Diederick C., Nyström, Marcus, Kasneci, Enkelejda

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, we evaluate SAM's ability to segment features from eye images recorded

Externí odkaz: http://arxiv.org/abs/2311.08077

Zobrazit plný text záznamu

Report

LEyes: A Lightweight Framework for Deep Learning-Based Eye Tracking using Synthetic Eye Images

Autor: Byrne, Sean Anthony, Maquiling, Virmarie, Nyström, Marcus, Kasneci, Enkelejda, Niehorster, Diederick C.

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-induced variations in eye images and inherent biological differences acro

Externí odkaz: http://arxiv.org/abs/2309.06129

Zobrazit plný text záznamu

Report

Precise localization of corneal reflections in eye images using deep learning trained on synthetic data

Autor: Byrne, Sean Anthony, Nyström, Marcus, Maquiling, Virmarie, Kasneci, Enkelejda, Niehorster, Diederick C.

We present a deep learning method for accurately localizing the center of a single corneal reflection (CR) in an eye image. Unlike previous approaches, we use a convolutional neural network (CNN) that was trained solely using simulated data. Using on

Externí odkaz: http://arxiv.org/abs/2304.05673

Zobrazit plný text záznamu