FaceVR: Real-Time Facial Reenactment and Eye Gaze Control in Virtual Reality

TL;DR

FaceVR introduces a real-time, image-based facial reenactment system for VR teleconferencing that achieves near photo-realistic results and allows dynamic facial and gaze modifications.

Contribution

The paper presents a novel real-time facial motion capture and eye tracking method that enables photo-realistic VR teleconferencing using prerecorded stereo videos.

Findings

Achieves near photo-realistic facial reenactment in VR

Enables real-time eye gaze control from monocular videos

Allows facial expression and gaze modifications during VR sessions

Abstract

We propose FaceVR, a novel image-based method that enables video teleconferencing in VR based on self-reenactment. State-of-the-art face tracking methods in the VR context are focused on the animation of rigged 3d avatars. While they achieve good tracking performance the results look cartoonish and not real. In contrast to these model-based approaches, FaceVR enables VR teleconferencing using an image-based technique that results in nearly photo-realistic outputs. The key component of FaceVR is a robust algorithm to perform real-time facial motion capture of an actor who is wearing a head-mounted display (HMD), as well as a new data-driven approach for eye tracking from monocular videos. Based on reenactment of a prerecorded stereo video of the person without the HMD, FaceVR incorporates photo-realistic re-rendering in real time, thus allowing artificial modifications of face and eye appearances. For instance, we can alter facial expressions or change gaze directions in the prerecorded target video. In a live setup, we apply these newly-introduced algorithmic components.