Eye Semantic Segmentation with a Lightweight Model
This work addresses the problem of efficient eye segmentation for real-time applications like VR/AR, though it is incremental as it builds on existing encoder-decoder and depthwise convolution techniques.
The paper tackles real-time eye semantic segmentation under hardware constraints by proposing a lightweight encoder-decoder model using depthwise convolution, achieving a mean intersection over union (mIoU) of 94.85% with a model size of 0.4 megabytes on the OpenEDS dataset.
In this paper, we present a multi-class eye segmentation method that can run the hardware limitations for real-time inference. Our approach includes three major stages: get a grayscale image from the input, segment three distinct eye region with a deep network, and remove incorrect areas with heuristic filters. Our model based on the encoder decoder structure with the key is the depthwise convolution operation to reduce the computation cost. We experiment on OpenEDS, a large scale dataset of eye images captured by a head-mounted display with two synchronized eye facing cameras. We achieved the mean intersection over union (mIoU) of 94.85% with a model of size 0.4 megabytes. The source code are available https://github.com/th2l/Eye_VR_Segmentation