首个无需依赖骨骼结构的人体动作预测模型，可跨数据集通用。
EquiFusion: Kinematics-Agnostic Human Motion Prediction via Equivariant Latent Diffusion
- 用等变架构将骨骼连接关系作为输入，自动适应不同关节顺序。
- 在多个基准上达顶尖性能，模型体积小75%，训练推理更快。
- 适合需要跨数据集迁移、部分观测或指定肢体生成的场景。
现有随机3D人体动作预测模型因硬编码骨骼运动学结构，严重限制泛化能力，难以跨数据集训练，且需复杂的数据重定向。我们提出EquiFusion，首个无运动学依赖的模型，采用具有排列等变性的潜在扩散架构。该模型将骨骼连通性作为显式输入参数，使内部计算天然对关节排序和图结构无关。这一设计实现了真正意义上的跨数据集泛化，解锁零样本新方向，如基于部分或遮挡观测的动作预测、特定肢体生成。EquiFusion在主流基准上达到领先水平，相比以往运动学特定方法模型缩小75%，同时实现更快训练与推理。该工作为鲁棒人体动作预测树立了新标准。模型与训练代码见https://ceveloper.github.io/publications/equifusion/。
原文摘要 · Abstract (English)
Existing Stochastic 3D Human Motion Prediction models are fundamentally constrained by hard-coding the skeleton kinematics, severely limiting generalization, preventing cross-dataset training, and requiring complex data retargeting. We introduce EquiFusion, the first kinematics-agnostic model to solve this bottleneck, implementing a latent diffusion model with a permutation equivariant architecture. EquiFusion treats the kinematics' connectivity as an explicit input parameter, ensuring its internal computations are inherently agnostic to joint ordering and graph structure. This novel design enables truly cross-dataset generalization to unseen kinematics and unlocks novel zero-shot directions, such as motion prediction from partial or occluded observations and targeted limb generation. EquiFusion achieves state-of-the-art results on major benchmarks, being up to 75% more compact than previous kinematics-specific methods, while achieving faster training and inference. EquiFusion thus establishes a new, flexible standard for robust human motion prediction. Model and training code are available at https://ceveloper.github.io/publications/equifusion/.
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。