English

High-fidelity Face Tracking for AR/VR via Deep Lighting Adaptation

Computer Vision and Pattern Recognition 2021-03-31 v1 Image and Video Processing

Abstract

3D video avatars can empower virtual communications by providing compression, privacy, entertainment, and a sense of presence in AR/VR. Best 3D photo-realistic AR/VR avatars driven by video, that can minimize uncanny effects, rely on person-specific models. However, existing person-specific photo-realistic 3D models are not robust to lighting, hence their results typically miss subtle facial behaviors and cause artifacts in the avatar. This is a major drawback for the scalability of these models in communication systems (e.g., Messenger, Skype, FaceTime) and AR/VR. This paper addresses previous limitations by learning a deep learning lighting model, that in combination with a high-quality 3D face tracking algorithm, provides a method for subtle and robust facial motion transfer from a regular video to a 3D photo-realistic avatar. Extensive experimental validation and comparisons to other state-of-the-art methods demonstrate the effectiveness of the proposed framework in real-world scenarios with variability in pose, expression, and illumination. Please visit https://www.youtube.com/watch?v=dtz1LgZR8cc for more results. Our project page can be found at https://www.cs.rochester.edu/u/lchen63.

Keywords

Cite

@article{arxiv.2103.15876,
  title  = {High-fidelity Face Tracking for AR/VR via Deep Lighting Adaptation},
  author = {Lele Chen and Chen Cao and Fernando De la Torre and Jason Saragih and Chenliang Xu and Yaser Sheikh},
  journal= {arXiv preprint arXiv:2103.15876},
  year   = {2021}
}

Comments

The paper is accepted to CVPR 2021

R2 v1 2026-06-24T00:39:53.648Z