用非各向同性扩散模型生成更自然的人体动作，避免肢体拉伸问题。
Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction
- 基于人体骨骼结构设计非各向同性高斯扩散机制
- 在真实数据集上优于传统方法，减少肢体扭曲和抖动
- 适合需要高质量动作生成的虚拟人、游戏开发场景
概率式人体动作预测旨在从历史观测中生成多个可能的未来动作。尽管现有方法在多样性和真实性方面表现良好，但常产生未被检测到的肢体拉伸和抖动。为此，我们提出SkeletonDiffusion，一种在架构与训练中嵌入人体身体先验知识的潜在扩散模型。该模型采用新型非各向同性高斯扩散公式，契合人体骨骼的自然运动学结构。结果表明，本方法显著优于传统的各向同性模型，在保持高多样性的同时，持续生成更真实的动作，有效避免肢体畸变等伪影。此外，我们指出常用多样性评估指标存在缺陷，可能无意中偏好同一序列内肢体长度不一致的模型。SkeletonDiffusion在真实世界数据集上建立了新基准，多项评估指标超越各类基线。项目页：https://ceveloper.github.io/publications/skeletondiffusion/
原文摘要 · Abstract (English)
Probabilistic human motion prediction aims to forecast multiple possible future movements from past observations. While current approaches report high diversity and realism, they often generate motions with undetected limb stretching and jitter. To address this, we introduce SkeletonDiffusion, a latent diffusion model that embeds an explicit inductive bias on the human body within its architecture and training. Our model is trained with a novel nonisotropic Gaussian diffusion formulation that aligns with the natural kinematic structure of the human skeleton. Results show that our approach outperforms conventional isotropic alternatives, consistently generating realistic predictions while avoiding artifacts such as limb distortion. Additionally, we identify a limitation in commonly used diversity metrics, which may inadvertently favor models that produce inconsistent limb lengths within the same sequence. SkeletonDiffusion sets a new benchmark on real-world datasets, outperforming various baselines across multiple evaluation metrics. Visit our project page at https://ceveloper.github.io/publications/skeletondiffusion/ .
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。