SILK: Smooth InterpoLation frameworK for motion in-betweening A Simplified Computational Approach

Motion in-betweening is a crucial tool for animators, enabling intricate control over pose-level details in each keyframe. Recent machine learning solutions for motion in-betweening rely on complex models, incorporating skeleton-aware architectures or requiring multiple modules and training steps. In this work, we introduce a simple yet effective Transformer-based framework, employing a single Transformer encoder to synthesize realistic motions for motion in-betweening tasks. We find that data modeling choices play a significant role in improving in-betweening performance. Among others, we show that increasing data volume can yield equivalent or improved motion transitions, that the choice of pose representation is vital for achieving high-quality results, and that incorporating velocity input features enhances animation performance. These findings challenge the assumption that model complexity is the primary determinant of animation quality and provide insights into a more data-centric approach to motion interpolation. Additional videos and supplementary material are available atthis https URL.

@article{akhoundi2025_2506.09075,
  title={ SILK: Smooth InterpoLation frameworK for motion in-betweening A Simplified Computational Approach },
  author={ Elly Akhoundi and Hung Yu Ling and Anup Anand Deshmukh and Judith Butepage },
  journal={arXiv preprint arXiv:2506.09075},
  year={ 2025 }
}