FNeVR: Neural Volume Rendering for Face Animation
This addresses the problem of realistic face animation for computer vision applications, representing an incremental improvement through a novel hybrid method.
The paper tackles the challenge of generating identity-preserving and photo-realistic face animations by proposing FNeVR, a network that combines 2D motion warping and 3D volume rendering, achieving the best overall quality and performance on widely used talking-head benchmarks.
Face animation, one of the hottest topics in computer vision, has achieved a promising performance with the help of generative models. However, it remains a critical challenge to generate identity preserving and photo-realistic images due to the sophisticated motion deformation and complex facial detail modeling. To address these problems, we propose a Face Neural Volume Rendering (FNeVR) network to fully explore the potential of 2D motion warping and 3D volume rendering in a unified framework. In FNeVR, we design a 3D Face Volume Rendering (FVR) module to enhance the facial details for image rendering. Specifically, we first extract 3D information with a well-designed architecture, and then introduce an orthogonal adaptive ray-sampling module for efficient rendering. We also design a lightweight pose editor, enabling FNeVR to edit the facial pose in a simple yet effective way. Extensive experiments show that our FNeVR obtains the best overall quality and performance on widely used talking-head benchmarks.