arXiv Open Access 2020

3D Human Motion Estimation via Motion Compression and Refinement

Zhengyi Luo S. Alireza Golestaneh Kris M. Kitani
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (3)

Z

Zhengyi Luo

S

S. Alireza Golestaneh

K

Kris M. Kitani

Format Sitasi

Luo, Z., Golestaneh, S.A., Kitani, K.M. (2020). 3D Human Motion Estimation via Motion Compression and Refinement. https://arxiv.org/abs/2008.03789

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2020
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓