CondSeg: Ellipse Estimation of Pupil and Iris via Conditioned Segmentation
This addresses the need for efficient eye component parsing in AR/VR products, though it appears to be an incremental improvement over existing segmentation and regression methods.
The paper tackles the problem of estimating elliptical parameters for pupil and iris from eye images by introducing CondSeg, which uses conditioned segmentation to directly predict these parameters from segmentation labels without requiring explicit ellipse annotations. The method achieves competitive segmentation results on OpenEDS datasets while providing accurate elliptical parameters for eye tracking applications.
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.