用单步生成预测人体动作，速度比现有方法快100倍
HumanCM: One Step Human Motion Prediction
- 基于一致性模型，一步完成动作生成
- 在Human3.6M和HumanEva-I上精度媲美顶尖扩散模型
- 适合需要快速推理的动作预测场景
我们提出HumanCM，一种基于一致性模型的一步式人体动作预测框架。与依赖多步去噪的扩散模型不同，HumanCM通过学习噪声状态与干净状态之间的自一致性映射，实现高效的单步生成。该框架采用基于Transformer的时空架构，并引入时间嵌入以建模长时依赖关系，保持动作连贯性。在Human3.6M和HumanEva-I数据集上的实验表明，HumanCM在预测精度上达到或超过当前最优扩散模型，同时将推理步数减少高达两个数量级。
原文摘要 · Abstract (English)
We present HumanCM, a one-step human motion prediction framework built upon consistency models. Instead of relying on multi-step denoising as in diffusion-based methods, HumanCM performs efficient single-step generation by learning a self-consistent mapping between noisy and clean motion states. The framework adopts a Transformer-based spatiotemporal architecture with temporal embeddings to model long-range dependencies and preserve motion coherence. Experiments on Human3.6M and HumanEva-I demonstrate that HumanCM achieves comparable or superior accuracy to state-of-the-art diffusion models while reducing inference steps by up to two orders of magnitude.
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。