# Real-time 3D Face-Eye Performance Capture of a Person Wearing VR Headset

## TL;DR

This paper introduces a real-time CNN-based system for capturing 3D face and eye movements of HMD users, enabling personalized avatars for immersive VR communication despite occlusions.

## Contribution

A novel deep learning approach that captures 3D facial and eye performance in real time without device modifications, using synthetic and collected datasets.

## Key findings

- Real-time 3D face and eye capture achieved.
- System produces personalized avatars with accurate identity, pose, and expression.
- Effective handling of occlusions caused by VR headsets.

## Abstract

Teleconference or telepresence based on virtual reality (VR) headmount display (HMD) device is a very interesting and promising application since HMD can provide immersive feelings for users. However, in order to facilitate face-to-face communications for HMD users, real-time 3D facial performance capture of a person wearing HMD is needed, which is a very challenging task due to the large occlusion caused by HMD. The existing limited solutions are very complex either in setting or in approach as well as lacking the performance capture of 3D eye gaze movement. In this paper, we propose a convolutional neural network (CNN) based solution for real-time 3D face-eye performance capture of HMD users without complex modification to devices. To address the issue of lacking training data, we generate massive pairs of HMD face-label dataset by data synthesis as well as collecting VR-IR eye dataset from multiple subjects. Then, we train a dense-fitting network for facial region and an eye gaze network to regress 3D eye model parameters. Extensive experimental results demonstrate that our system can efficiently and effectively produce in real time a vivid personalized 3D avatar with the correct identity, pose, expression and eye motion corresponding to the HMD user.