0

Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling

A two-stage neural network framework utilizes joint-level tokens and transformers to generate accurate and smooth full-body avatar motions from head and hand-tracking data.

Year
2023
Venue
ICCV 2023 1
Authors
5
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2308.08855ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

To bridge the physical and virtual worlds for rapidly developed VR/AR applications, the ability to realistically drive 3D full-body avatars is of great significance. Although real-time body tracking with only the head-mounted displays (HMDs) and hand controllers is heavily under-constrained, a carefully designed end-to-end neural network is of great potential to solve the problem by learning from large-scale motion data. To this end, we propose a two-stage framework that can obtain accurate and smooth full-body motions with the three tracking signals of head and hands only. Our framework explicitly models the joint-level features in the first stage and utilizes them as spatiotemporal tokens for alternating spatial and temporal transformer blocks to capture joint-level correlations in the second stage. Furthermore, we design a set of loss terms to constrain the task of a high degree of freedom, such that we can exploit the potential of our joint-level modeling. With extensive experiments on the AMASS motion dataset and real-captured data, we validate the effectiveness of our designs and show our proposed method can achieve more accurate and smooth motion compared to existing approaches.

Authors

5