Towards Unsupervised Eye-Region Segmentation for Eye Tracking

TL;DR

This paper introduces an unsupervised method for eye-region segmentation that leverages priors, foundation models, and progressive learning to achieve high accuracy without manual labeling, advancing eye tracking technology.

Contribution

It presents a novel unsupervised framework combining priors and foundation models for precise eye-region segmentation in eye tracking.

Findings

Achieves 90% accuracy for pupil and iris segmentation.

Achieves 85% accuracy for whole eye-region segmentation.

Reduces reliance on manual annotations in training.

Abstract

Finding the eye and parsing out the parts (e.g. pupil and iris) is a key prerequisite for image-based eye tracking, which has become an indispensable module in today's head-mounted VR/AR devices. However, a typical route for training a segmenter requires tedious handlabeling. In this work, we explore an unsupervised way. First, we utilize priors of human eye and extract signals from the image to establish rough clues indicating the eye-region structure. Upon these sparse and noisy clues, a segmentation network is trained to gradually identify the precise area for each part. To achieve accurate parsing of the eye-region, we first leverage the pretrained foundation model Segment Anything (SAM) in an automatic way to refine the eye indications. Then, the learning process is designed in an end-to-end manner following progressive and prior-aware principle. Experiments show that our unsupervised approach can easily achieve 90% (the pupil and iris) and 85% (the whole eye-region) of the performances under supervised learning.