arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.03789cs.CV
收藏

基于运动压缩和细化的三维人体运动估计

3D Human Motion Estimation via Motion Compression and Refinement

Carnegie Mellon University(卡内基梅隆大学)

Zhengyi Luo, S. Alireza Golestaneh, Kris M. Kitani

摘要:

我们开发了一种技术,从RGB视频序列生成平滑和准确的三维人体姿势和运动估计。我们的方法,我们称之为运动估计通过变分自编码器(MEVA),分解的时间序列的人体运动到一个平滑的运动表示,使用自动编码器为基础的运动压缩和残差表示通过运动细化学习。人体运动的这种两步编码在两个阶段中捕获人体运动:捕获粗略整体运动的一般人体运动估计步骤,以及添加回人特定运动细节的残差估计。实验表明,我们的方法产生平滑和准确的三维人体姿态和运动估计。

英文摘要:

We develop a technique for generating smooth and accurate 3D human pose and motion estimates from RGB video sequences. Our method, which we call Motion Estimation via Variational Autoencoder (MEVA), decomposes a temporal sequence of human motion into a smooth motion representation using auto-encoder-based motion compression and a residual representation learned through motion refinement. This two-step encoding of human motion captures human motion in two stages: a general human motion estimation step that captures the coarse overall motion, and a residual estimation that adds back person-specific motion details. Experiments show that our method produces both smooth and accurate 3D human pose and motion estimates.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑