用几何神经距离场建模人体运动先验，实现更真实连贯的3D动作恢复
Geometric Neural Distance Fields for Learning Human Motion Priors
- 在关节旋转、速度、加速度的乘积空间中构建神经距离场，显式建模运动几何结构
- 在AMASS数据集上训练，对噪声、部分观测等多类输入均实现显著性能提升
- 提出自适应投影与几何积分器，适合动作去噪、补全及2D/3D观测拟合任务
我们提出神经黎曼运动场（NRMF），一种新型3D生成式人体运动先验，可实现鲁棒、时间一致且物理合理的3D动作恢复。不同于现有基于变分自编码器或扩散模型的方法，我们的高阶运动先验将人体动作显式建模为一组对应于姿态、运动（速度）和加速度动态的神经距离场（NDFs）的零水平集。该框架在数学上严谨：所构造的NDFs定义在关节旋转、角速度和角加速度的乘积空间上，尊重底层关节约束的几何结构。我们进一步提出：(i) 一种新颖的自适应步长混合投影算法，用于映射到合理动作空间；(ii) 一种新型几何积分器，用于测试时优化与生成过程中的真实动作轨迹“滚动”生成。实验表明，该方法在多个任务上均有显著且一致的提升：在AMASS数据集上训练后，NRMF能良好泛化至多种输入模态，并适用于从去噪到动作插值，以及部分2D/3D观测拟合等多种任务。
原文摘要 · Abstract (English)
We introduce Neural Riemannian Motion Fields (NRMF), a novel 3D generative human motion prior that enables robust, temporally consistent, and physically plausible 3D motion recovery. Unlike existing VAE or diffusion-based methods, our higher-order motion prior explicitly models the human motion in the zero level set of a collection of neural distance fields (NDFs) corresponding to pose, transition (velocity), and acceleration dynamics. Our framework is rigorous in the sense that our NDFs are constructed on the product space of joint rotations, their angular velocities, and angular accelerations, respecting the geometry of the underlying articulations. We further introduce: (i) a novel adaptive-step hybrid algorithm for projecting onto the set of plausible motions, and (ii) a novel geometric integrator to "roll out" realistic motion trajectories during test-time-optimization and generation. Our experiments show significant and consistent gains: trained on the AMASS dataset, NRMF remarkably generalizes across multiple input modalities and to diverse tasks ranging from denoising to motion in-betweening and fitting to partial 2D / 3D observations.
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。