High-fidelity Face Tracking for AR/VR via Deep Lighting Adaptation
This addresses a major drawback for the scalability of photo-realistic avatars in communication systems and AR/VR, though it appears incremental as it builds on existing tracking methods with a new lighting adaptation component.
The paper tackles the problem of existing person-specific photo-realistic 3D avatars not being robust to lighting, which causes artifacts and misses subtle facial behaviors, by proposing a deep learning lighting model combined with high-quality 3D face tracking to enable robust facial motion transfer from video to avatars, with extensive experimental validation showing effectiveness in real-world scenarios.
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.