用单个Transformer实现高质量动作补间，强调数据设计比模型复杂度更重要。
SILK: Smooth InterpoLation frameworK for motion in-betweening A Simplified Computational Approach
- 仅用一个Transformer编码器完成动作补间生成
- 增加数据量和使用速度特征可显著提升动画质量
- 适合关注数据驱动与简化模型的动画研究者
动作补间是动画师精细控制关键帧姿态细节的重要工具。现有基于机器学习的补间方法依赖复杂模型，如骨骼感知架构或多个模块与训练步骤。本文提出一种简单高效的基于Transformer的框架，仅用一个Transformer编码器即可生成逼真的运动序列。我们发现数据建模选择对补间性能有显著影响：增加数据量可获得等效或更优的运动过渡效果；姿态表示的选择对高质量结果至关重要；引入速度输入特征能提升动画表现。这些发现挑战了‘模型越复杂越好’的假设，为动作插值提供了更数据驱动的新思路。更多视频与补充材料见 https://silk-paper.github.io。
原文摘要 · Abstract (English)
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 at https://silk-paper.github.io.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。