Adaptive Interpolation-Synthesis for Motion In-Betweening on Keyframe-Based Animation

TL;DR

This paper introduces an adaptive interpolation-synthesis method for keyframe-based 3D animation in production, improving efficiency and stylistic consistency by aligning with professional workflows.

Contribution

It proposes a novel AIS layer that balances learned interpolation and pose synthesis, tailored for professional animation environments.

Findings

Achieves state-of-the-art performance on production data.

Enables 3.5x speedup in in-betweening tasks within Autodesk Maya.

Improves stylistic consistency and alignment with real-world workflows.

Abstract

Motion in-betweening is one of the most artistically demanding and time consuming stages of 3D animation, where the expressivity and rhythm of motion are defined. The level of creative control it requires makes it a major production bottleneck, underscoring the need for intelligent tools that assist animators in this process. Although recent deep learning approaches have achieved strong results in motion synthesis and in-betweening, they assume data characteristics, motion styles, and problem formulations that diverge from professional animation workflows. To bridge this gap, we propose a method explicitly aligned with the constraints of motion in-betweening for keyframe-based animation in production environments. At its core, the Adaptive Interpolation-Synthesis (AIS) layer mirrors the animator's creative process by dynamically balancing learned interpolation and direct pose synthesis. In addition, a domain-based input keypose schedule reflects the distribution of production data, improving stylistic consistency and alignment between training and real-world usage. Our method achieves state-of-the-art performance on production data; when integrated into Autodesk Maya, it enables animators to complete in-betweening tasks with a 3.5x speedup.