99 citations
4 papers
Tiny is not small enough: High-quality, low-resource facial animation models through hybrid knowledge distillation
Zhen Han, Mattias Teye, Derek Yadgaroff +1
The training of high-quality, robust machine learning models for speech-driven 3D facial animation requires a large, diverse dataset of high-quality audio-animation pairs. To overc…
Evaluating the Evaluators: Towards Human-aligned Metrics for Missing Markers Reconstruction
Taras Kucherenko, Derek Peristy, Judith Bütepage
Animation data is often obtained through optical motion capture systems, which utilize a multitude of cameras to establish the position of optical markers. However, system errors o…
Improving Conditional Level Generation using Automated Validation in Match-3 Games
Monica Villanueva Aylagas, Joakim Bergdahl, Jonas Gillberg +3
Generative models for level generation have shown great potential in game production. However, they often provide limited control over the generation, and the validity of the gener…
A Comprehensive Review of Data-Driven Co-Speech Gesture Generation
Simbarashe Nyatsanga, Taras Kucherenko, Chaitanya Ahuja +2
Gestures that accompany speech are an essential part of natural and efficient embodied human communication. The automatic generation of such co-speech gestures is a long-standing p…