CoNFies: Controllable Neural Face Avatars
This work provides a solution for creating realistic and controllable 3D facial avatars from 2D images, which is incremental by automating control through facial action recognition.
The paper tackled the problem of synthesizing novel facial expressions with controllable neural face avatars by addressing the lack of interpretable control and the need for manual annotations in existing methods, achieving superior visual and anatomic fidelity compared to competing approaches.
Neural Radiance Fields (NeRF) are compelling techniques for modeling dynamic 3D scenes from 2D image collections. These volumetric representations would be well suited for synthesizing novel facial expressions but for two problems. First, deformable NeRFs are object agnostic and model holistic movement of the scene: they can replay how the motion changes over time, but they cannot alter it in an interpretable way. Second, controllable volumetric representations typically require either time-consuming manual annotations or 3D supervision to provide semantic meaning to the scene. We propose a controllable neural representation for face self-portraits (CoNFies), that solves both of these problems within a common framework, and it can rely on automated processing. We use automated facial action recognition (AFAR) to characterize facial expressions as a combination of action units (AU) and their intensities. AUs provide both the semantic locations and control labels for the system. CoNFies outperformed competing methods for novel view and expression synthesis in terms of visual and anatomic fidelity of expressions.