Real-Time Cleaning and Refinement of Facial Animation Signals
This addresses the need for real-time, high-quality facial animation in entertainment, though it is incremental as it builds on existing signal processing methods.
The paper tackled the problem of artifacts in real-time facial animation from motion capture by proposing a system that preserves natural dynamics, using a recurrent neural network to learn from clean data and showing qualitative improvements in retrieving natural motion from noisy inputs.
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.