MAGE:A Multi-stage Avatar Generator with Sparse Observations

TL;DR

MAGE is a multi-stage avatar generator that progressively infers full-body poses from sparse head-mounted device observations, improving motion realism and temporal consistency in AR/VR applications.

Contribution

It introduces a multi-stage, progressive prediction strategy that factorizes the motion mapping process, enhancing accuracy and realism over previous one-stage methods.

Findings

Outperforms state-of-the-art methods in accuracy

Produces more realistic and temporally consistent motions

Effective in large-scale dataset evaluations

Abstract

Inferring full-body poses from Head Mounted Devices, which capture only 3-joint observations from the head and wrists, is a challenging task with wide AR/VR applications. Previous attempts focus on learning one-stage motion mapping and thus suffer from an over-large inference space for unobserved body joint motions. This often leads to unsatisfactory lower-body predictions and poor temporal consistency, resulting in unrealistic or incoherent motion sequences. To address this, we propose a powerful Multi-stage Avatar GEnerator named MAGE that factorizes this one-stage direct motion mapping learning with a progressive prediction strategy. Specifically, given initial 3-joint motions, MAGE gradually inferring multi-scale body part poses at different abstract granularity levels, starting from a 6-part body representation and gradually refining to 22 joints. With decreasing abstract levels step by step, MAGE introduces more motion context priors from former prediction stages and thus improves realistic motion completion with richer constraint conditions and less ambiguity. Extensive experiments on large-scale datasets verify that MAGE significantly outperforms state-of-the-art methods with better accuracy and continuity.