Saved in:
Bibliographic Details
Main Authors: Jia, Zhuang, Deng, Jiangfan, Chi, Liying, Long, Xiang, Du, Daniel K.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.17231
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913486686126080
author Jia, Zhuang
Deng, Jiangfan
Chi, Liying
Long, Xiang
Du, Daniel K.
author_facet Jia, Zhuang
Deng, Jiangfan
Chi, Liying
Long, Xiang
Du, Daniel K.
contents Parsing of eye components (i.e. pupil, iris and sclera) is fundamental for eye tracking and gaze estimation for AR/VR products. Mainstream approaches tackle this problem as a multi-class segmentation task, providing only visible part of pupil/iris, other methods regress elliptical parameters using human-annotated full pupil/iris parameters. In this paper, we consider two priors: projected full pupil/iris circle can be modelled with ellipses (ellipse prior), and the visibility of pupil/iris is controlled by openness of eye-region (condition prior), and design a novel method CondSeg to estimate elliptical parameters of pupil/iris directly from segmentation labels, without explicitly annotating full ellipses, and use eye-region mask to control the visibility of estimated pupil/iris ellipses. Conditioned segmentation loss is used to optimize the parameters by transforming parameterized ellipses into pixel-wise soft masks in a differentiable way. Our method is tested on public datasets (OpenEDS-2019/-2020) and shows competitive results on segmentation metrics, and provides accurate elliptical parameters for further applications of eye tracking simultaneously.
format Preprint
id arxiv_https___arxiv_org_abs_2408_17231
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CondSeg: Ellipse Estimation of Pupil and Iris via Conditioned Segmentation
Jia, Zhuang
Deng, Jiangfan
Chi, Liying
Long, Xiang
Du, Daniel K.
Computer Vision and Pattern Recognition
Parsing of eye components (i.e. pupil, iris and sclera) is fundamental for eye tracking and gaze estimation for AR/VR products. Mainstream approaches tackle this problem as a multi-class segmentation task, providing only visible part of pupil/iris, other methods regress elliptical parameters using human-annotated full pupil/iris parameters. In this paper, we consider two priors: projected full pupil/iris circle can be modelled with ellipses (ellipse prior), and the visibility of pupil/iris is controlled by openness of eye-region (condition prior), and design a novel method CondSeg to estimate elliptical parameters of pupil/iris directly from segmentation labels, without explicitly annotating full ellipses, and use eye-region mask to control the visibility of estimated pupil/iris ellipses. Conditioned segmentation loss is used to optimize the parameters by transforming parameterized ellipses into pixel-wise soft masks in a differentiable way. Our method is tested on public datasets (OpenEDS-2019/-2020) and shows competitive results on segmentation metrics, and provides accurate elliptical parameters for further applications of eye tracking simultaneously.
title CondSeg: Ellipse Estimation of Pupil and Iris via Conditioned Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.17231