EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Jiaxi, Streli, Paul, Meier, Manuel, Holz, Christian
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909307111473152
author Jiang, Jiaxi
Streli, Paul
Meier, Manuel
Holz, Christian
author_facet Jiang, Jiaxi
Streli, Paul
Meier, Manuel
Holz, Christian
contents Full-body egocentric pose estimation from head and hand poses alone has become an active area of research to power articulate avatar representations on headset-based platforms. However, existing methods over-rely on the indoor motion-capture spaces in which datasets were recorded, while simultaneously assuming continuous joint motion capture and uniform body dimensions. We propose EgoPoser to overcome these limitations with four main contributions. 1) EgoPoser robustly models body pose from intermittent hand position and orientation tracking only when inside a headset's field of view. 2) We rethink input representations for headset-based ego-pose estimation and introduce a novel global motion decomposition method that predicts full-body pose independent of global positions. 3) We enhance pose estimation by capturing longer motion time series through an efficient SlowFast module design that maintains computational efficiency. 4) EgoPoser generalizes across various body shapes for different users. We experimentally evaluate our method and show that it outperforms state-of-the-art methods both qualitatively and quantitatively while maintaining a high inference speed of over 600fps. EgoPoser establishes a robust baseline for future work where full-body pose estimation no longer needs to rely on outside-in capture and can scale to large-scale and unseen environments.
format Preprint
id arxiv_https___arxiv_org_abs_2308_06493
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere
Jiang, Jiaxi
Streli, Paul
Meier, Manuel
Holz, Christian
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Human-Computer Interaction
68T07, 68T45, 68U01
I.2; I.3; I.4; I.5
Full-body egocentric pose estimation from head and hand poses alone has become an active area of research to power articulate avatar representations on headset-based platforms. However, existing methods over-rely on the indoor motion-capture spaces in which datasets were recorded, while simultaneously assuming continuous joint motion capture and uniform body dimensions. We propose EgoPoser to overcome these limitations with four main contributions. 1) EgoPoser robustly models body pose from intermittent hand position and orientation tracking only when inside a headset's field of view. 2) We rethink input representations for headset-based ego-pose estimation and introduce a novel global motion decomposition method that predicts full-body pose independent of global positions. 3) We enhance pose estimation by capturing longer motion time series through an efficient SlowFast module design that maintains computational efficiency. 4) EgoPoser generalizes across various body shapes for different users. We experimentally evaluate our method and show that it outperforms state-of-the-art methods both qualitatively and quantitatively while maintaining a high inference speed of over 600fps. EgoPoser establishes a robust baseline for future work where full-body pose estimation no longer needs to rely on outside-in capture and can scale to large-scale and unseen environments.
title EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Human-Computer Interaction
68T07, 68T45, 68U01
I.2; I.3; I.4; I.5
url https://arxiv.org/abs/2308.06493