November
2020
3D Human Motion Estimation via Motion Compression and Refinement
Authors:
Abstract:
We develop a technique for generating smooth and accurate 3D human pose and motion estimates from RGB video sequences. Our technique, 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 process of human motion can represent a wide variety of general human motions while also retaining person-specific motion details. Experiments show that our method produces both smooth and accurate 3D human pose and motion estimates.
copied = false, 2000);
">
@conference{Luo-2020-126385,
author = {Zhengyi Luo And S. Alireza Golestaneh And Kris M. Kitani},
title = {3D Human Motion Estimation via Motion Compression and Refinement},
booktitle = {Proceedings of Asian Conference on Computer Vision (ACCV '20)},
year = {2020},
month = {November},
pages = {324 - 340},
}
author = {Zhengyi Luo And S. Alireza Golestaneh And Kris M. Kitani},
title = {3D Human Motion Estimation via Motion Compression and Refinement},
booktitle = {Proceedings of Asian Conference on Computer Vision (ACCV '20)},
year = {2020},
month = {November},
pages = {324 - 340},
}