TY  - JOUR
TI  - Adaptive Interpolation-Synthesis for Motion In-Betweening on Keyframe-Based Animation
AU  - Anton Raël
AU  - Julien Boucher
AU  - Antoine Lhermitte
PY  - 2026
DA  - 2026/05/04/
JO  - SIGGRAPH 2026 Conference Papers / arXiv
AB  - A SIGGRAPH 2026 conference paper from Animaj (Paris) describing the machine learning method behind the studio's production in-betweening tool. The Adaptive Interpolation-Synthesis (AIS) layer, combined with a bidirectional LSTM encoder, mirrors the animator's process by dynamically blending learned interpolation with direct pose synthesis, and a domain-based input keypose schedule aligns training with real production data. Integrated into Autodesk Maya, the studio reports in-betweening completed up to 3.5 times faster while preserving motion style. In-betweening is a foundational taught skill, and this is a rare production-proven, peer-reviewed account of restructuring that stage around machine learning while keeping the animator's blocking-to-polish workflow.
KW  - machine-learning
KW  - character-animation
KW  - in-betweening
KW  - production-pipelines
KW  - studio-adoption
UR  - https://arxiv.org/abs/2605.02742
LA  - en
ER  -