跨骨骼拓扑的运动融合，让不同角色间自然过渡动作。
Neural Motion Blending Across Arbitrary Character Topologies
- 用语义编码器提取动作状态隐向量，结合扩散解码器生成角色特定动作。
- 在真骨动物园数据集上实现不同骨骼结构角色间的平滑动作融合。
- 适合需要跨角色动画重用的制作人员，尤其适用于骨骼差异大的场景。
角色动画中的运动融合可通过对已有动作样本进行插值来合成新动作。现有方法通常受限于固定骨架拓扑，要求角色间具有相同或近似相同的骨骼结构。本文提出一种面向异构骨架的新型运动融合框架。该架构结合语义编码器（提取每帧动作状态的隐表示）与基于扩散的解码器（根据隐码重建角色特定动作）。推理时，通过插值两个输入动作的隐表示获得融合动作。我们在Truebones Zoo数据集上训练并评估该方法，使用相同与不同骨架拓扑的动作进行实验，证明其在多种场景下均能实现流畅且合理的运动融合。
原文摘要 · Abstract (English)
Motion blending in character animation enables the synthesis of new motions by interpolating between existing examples. Current methods are typically restricted to fixed skeleton topologies, requiring identical or near-identical skeletal structures across characters. We present a novel framework for motion blending across heterogeneous skeletons. The proposed architecture combines a semantic encoder, which extracts per-frame latent representations of the motion state, with a diffusion-based decoder, which reconstructs character-specific motion conditioned on this latent code. At inference, blended motions are obtained by interpolating the latent representations of two input motions. We train and evaluate the method on the Truebones Zoo dataset using motions defined on both same and distinct skeleton topologies, demonstrating the ability to achieve smooth and plausible blending in a variety of scenarios.
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。