Real-Time Cleaning and Refinement of Facial Animation Signals

TL;DR

This paper introduces a real-time facial animation refinement system that uses neural networks to preserve natural motion dynamics, improving the quality of noisy or degraded animation signals in real-time applications.

Contribution

It presents a novel neural network-based approach that preserves and restores natural facial motion dynamics in real-time animation signals, unlike traditional filtering methods.

Findings

Successfully retrieves natural facial motion from noisy inputs

Operates at any framerate due to derivative parametrization

Enhances real-time animation quality with preserved dynamics

Abstract

With the increasing demand for real-time animated 3D content in the entertainment industry and beyond, performance-based animation has garnered interest among both academic and industrial communities. While recent solutions for motion-capture animation have achieved impressive results, handmade post-processing is often needed, as the generated animations often contain artifacts. Existing real-time motion capture solutions have opted for standard signal processing methods to strengthen temporal coherence of the resulting animations and remove inaccuracies. While these methods produce smooth results, they inherently filter-out part of the dynamics of facial motion, such as high frequency transient movements. In this work, we propose a real-time animation refining system that preserves -- or even restores -- the natural dynamics of facial motions. To do so, we leverage an off-the-shelf recurrent neural network architecture that learns proper facial dynamics patterns on clean animation data. We parametrize our system using the temporal derivatives of the signal, enabling our network to process animations at any framerate. Qualitative results show that our system is able to retrieve natural motion signals from noisy or degraded input animation.