HMD-NeMo: Online 3D Avatar Motion Generation From Sparse Observations

TL;DR

HMD-NeMo is a real-time neural network that generates full body avatar motion from sparse, partially visible hand and head signals in mixed reality, addressing the challenge of limited input visibility.

Contribution

It introduces the first unified approach for full body motion prediction from partial hand observations without full hand visibility in mixed reality.

Findings

Achieves state-of-the-art results on AMASS dataset.

Operates in online, real-time fashion.

Effectively handles partial hand visibility scenarios.

Abstract

Generating both plausible and accurate full body avatar motion is the key to the quality of immersive experiences in mixed reality scenarios. Head-Mounted Devices (HMDs) typically only provide a few input signals, such as head and hands 6-DoF. Recently, different approaches achieved impressive performance in generating full body motion given only head and hands signal. However, to the best of our knowledge, all existing approaches rely on full hand visibility. While this is the case when, e.g., using motion controllers, a considerable proportion of mixed reality experiences do not involve motion controllers and instead rely on egocentric hand tracking. This introduces the challenge of partial hand visibility owing to the restricted field of view of the HMD. In this paper, we propose the first unified approach, HMD-NeMo, that addresses plausible and accurate full body motion generation even when the hands may be only partially visible. HMD-NeMo is a lightweight neural network that predicts the full body motion in an online and real-time fashion. At the heart of HMD-NeMo is the spatio-temporal encoder with novel temporally adaptable mask tokens that encourage plausible motion in the absence of hand observations. We perform extensive analysis of the impact of different components in HMD-NeMo and introduce a new state-of-the-art on AMASS dataset through our evaluation.