用确定性映射+随机生成，让动作合成更稳定多样
Deterministic-to-Stochastic Diverse Latent Feature Mapping for Human Motion Synthesis
- 先学动作潜在分布，再通过确定性映射连接高斯分布
- 生成动作多样性提升，且不增加额外训练参数
- 适合需要高质量多样动作生成的研究与应用
人体动作合成旨在生成合理的人体运动序列，在计算机动画领域备受关注。近年来基于得分的生成模型（SGMs）在此任务上表现优异，但其训练过程涉及复杂的曲率轨迹，导致训练不稳定。本文提出一种确定性到随机的多样化潜在特征映射方法（DSDFM），包含两个阶段：第一阶段为人体动作重建，学习动作的潜在空间分布；第二阶段为多样化动作生成，建立高斯分布与动作潜在分布之间的联系，从而提升生成动作的多样性和准确性。该阶段通过设计的确定性特征映射（DerODE）和随机多样化输出生成（DivSDE）实现。相比以往基于SGMs的方法，DSDFM训练更简单，且在不引入额外训练参数的情况下增强多样性。定性与定量实验表明，DSDFM达到当前最优性能，验证了其在人体动作合成中的优越性。
原文摘要 · Abstract (English)
Human motion synthesis aims to generate plausible human motion sequences, which has raised widespread attention in computer animation. Recent score-based generative models (SGMs) have demonstrated impressive results on this task. However, their training process involves complex curvature trajectories, leading to unstable training process. In this paper, we propose a Deterministic-to-Stochastic Diverse Latent Feature Mapping (DSDFM) method for human motion synthesis. DSDFM consists of two stages. The first human motion reconstruction stage aims to learn the latent space distribution of human motions. The second diverse motion generation stage aims to build connections between the Gaussian distribution and the latent space distribution of human motions, thereby enhancing the diversity and accuracy of the generated human motions. This stage is achieved by the designed deterministic feature mapping procedure with DerODE and stochastic diverse output generation procedure with DivSDE.DSDFM is easy to train compared to previous SGMs-based methods and can enhance diversity without introducing additional training parameters.Through qualitative and quantitative experiments, DSDFM achieves state-of-the-art results surpassing the latest methods, validating its superiority in human motion synthesis.
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。