综述人体运动预测、重建与生成的最新进展与应用。
Human Motion Prediction, Reconstruction, and Generation
- 基于变换器、扩散模型等方法提升运动建模精度。
- 实现从视觉输入中恢复高精度3D人体动作。
- 支持文本/环境约束生成多样真实运动，适用于游戏与机器人。
本报告综述了人体运动预测、重建与生成领域的最新进展。运动预测旨在从历史数据中预测未来姿态与动作，应对非线性动力学、遮挡和运动风格变化等挑战。运动重建致力于从视觉输入中恢复精确的3D人体运动，常结合基于变换器的架构、扩散模型及物理一致性损失以处理噪声与复杂姿态。运动生成则根据动作标签、文本描述或环境约束合成真实且多样的动作，广泛应用于机器人、游戏与虚拟角色。此外，文本到动作生成与人-物交互建模日益受到关注，推动增强现实与机器人领域实现细粒度、上下文感知的动作合成。报告总结了关键技术、常用数据集、现存挑战及未来研究方向，促进该领域持续发展。
原文摘要 · Abstract (English)
This report reviews recent advancements in human motion prediction, reconstruction, and generation. Human motion prediction focuses on forecasting future poses and movements from historical data, addressing challenges like nonlinear dynamics, occlusions, and motion style variations. Reconstruction aims to recover accurate 3D human body movements from visual inputs, often leveraging transformer-based architectures, diffusion models, and physical consistency losses to handle noise and complex poses. Motion generation synthesizes realistic and diverse motions from action labels, textual descriptions, or environmental constraints, with applications in robotics, gaming, and virtual avatars. Additionally, text-to-motion generation and human-object interaction modeling have gained attention, enabling fine-grained and context-aware motion synthesis for augmented reality and robotics. This review highlights key methodologies, datasets, challenges, and future research directions driving progress in these fields.
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。