XR-MBT: Multi-modal Full Body Tracking for XR through Self-Supervision with Learned Depth Point Cloud Registration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rozumnyi, Denys, Bertsch, Nadine, Sbai, Othman, Arcadu, Filippo, Chen, Yuhua, Sanakoyeu, Artsiom, Kumar, Manoj, Herold, Catherine, Kips, Robin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915037349675008
author Rozumnyi, Denys
Bertsch, Nadine
Sbai, Othman
Arcadu, Filippo
Chen, Yuhua
Sanakoyeu, Artsiom
Kumar, Manoj
Herold, Catherine
Kips, Robin
author_facet Rozumnyi, Denys
Bertsch, Nadine
Sbai, Othman
Arcadu, Filippo
Chen, Yuhua
Sanakoyeu, Artsiom
Kumar, Manoj
Herold, Catherine
Kips, Robin
contents Tracking the full body motions of users in XR (AR/VR) devices is a fundamental challenge to bring a sense of authentic social presence. Due to the absence of dedicated leg sensors, currently available body tracking methods adopt a synthesis approach to generate plausible motions given a 3-point signal from the head and controller tracking. In order to enable mixed reality features, modern XR devices are capable of estimating depth information of the headset surroundings using available sensors combined with dedicated machine learning models. Such egocentric depth sensing cannot drive the body directly, as it is not registered and is incomplete due to limited field-of-view and body self-occlusions. For the first time, we propose to leverage the available depth sensing signal combined with self-supervision to learn a multi-modal pose estimation model capable of tracking full body motions in real time on XR devices. We demonstrate how current 3-point motion synthesis models can be extended to point cloud modalities using a semantic point cloud encoder network combined with a residual network for multi-modal pose estimation. These modules are trained jointly in a self-supervised way, leveraging a combination of real unregistered point clouds and simulated data obtained from motion capture. We compare our approach against several state-of-the-art systems for XR body tracking and show that our method accurately tracks a diverse range of body motions. XR-MBT tracks legs in XR for the first time, whereas traditional synthesis approaches based on partial body tracking are blind.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18377
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle XR-MBT: Multi-modal Full Body Tracking for XR through Self-Supervision with Learned Depth Point Cloud Registration
Rozumnyi, Denys
Bertsch, Nadine
Sbai, Othman
Arcadu, Filippo
Chen, Yuhua
Sanakoyeu, Artsiom
Kumar, Manoj
Herold, Catherine
Kips, Robin
Computer Vision and Pattern Recognition
Machine Learning
Tracking the full body motions of users in XR (AR/VR) devices is a fundamental challenge to bring a sense of authentic social presence. Due to the absence of dedicated leg sensors, currently available body tracking methods adopt a synthesis approach to generate plausible motions given a 3-point signal from the head and controller tracking. In order to enable mixed reality features, modern XR devices are capable of estimating depth information of the headset surroundings using available sensors combined with dedicated machine learning models. Such egocentric depth sensing cannot drive the body directly, as it is not registered and is incomplete due to limited field-of-view and body self-occlusions. For the first time, we propose to leverage the available depth sensing signal combined with self-supervision to learn a multi-modal pose estimation model capable of tracking full body motions in real time on XR devices. We demonstrate how current 3-point motion synthesis models can be extended to point cloud modalities using a semantic point cloud encoder network combined with a residual network for multi-modal pose estimation. These modules are trained jointly in a self-supervised way, leveraging a combination of real unregistered point clouds and simulated data obtained from motion capture. We compare our approach against several state-of-the-art systems for XR body tracking and show that our method accurately tracks a diverse range of body motions. XR-MBT tracks legs in XR for the first time, whereas traditional synthesis approaches based on partial body tracking are blind.
title XR-MBT: Multi-modal Full Body Tracking for XR through Self-Supervision with Learned Depth Point Cloud Registration
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2411.18377