3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow
This addresses the need for precise facial movement capture in applications like animation and virtual reality, representing a strong specific gain in monocular 3D face tracking.
The paper tackles the problem of accurate 3D face tracking from 2D video by proposing FlowFace, which uses a dense per-vertex alignment network trained on high-quality 3D scans and achieves superior performance on benchmarks, leading to improved 3D data generation for downstream tasks.
When working with 3D facial data, improving fidelity and avoiding the uncanny valley effect is critically dependent on accurate 3D facial performance capture. Because such methods are expensive and due to the widespread availability of 2D videos, recent methods have focused on how to perform monocular 3D face tracking. However, these methods often fall short in capturing precise facial movements due to limitations in their network architecture, training, and evaluation processes. Addressing these challenges, we propose a novel face tracker, FlowFace, that introduces an innovative 2D alignment network for dense per-vertex alignment. Unlike prior work, FlowFace is trained on high-quality 3D scan annotations rather than weak supervision or synthetic data. Our 3D model fitting module jointly fits a 3D face model from one or many observations, integrating existing neutral shape priors for enhanced identity and expression disentanglement and per-vertex deformations for detailed facial feature reconstruction. Additionally, we propose a novel metric and benchmark for assessing tracking accuracy. Our method exhibits superior performance on both custom and publicly available benchmarks. We further validate the effectiveness of our tracker by generating high-quality 3D data from 2D videos, which leads to performance gains on downstream tasks.