EnvPoser: Environment-aware Realistic Human Motion Estimation from Sparse Observations with Uncertainty Modeling

TL;DR

EnvPoser is a novel two-stage framework that estimates full-body human motion from sparse VR signals by modeling multiple hypotheses and incorporating environmental constraints, leading to more realistic and accurate motion predictions.

Contribution

The paper introduces EnvPoser, a new method combining uncertainty modeling and environment-aware refinement for improved motion estimation from sparse observations.

Findings

Achieves state-of-the-art performance on public datasets.

Significantly improves motion-environment interaction estimation.

Effectively models multi-hypothesis human motion.

Abstract

Estimating full-body motion using the tracking signals of head and hands from VR devices holds great potential for various applications. However, the sparsity and unique distribution of observations present a significant challenge, resulting in an ill-posed problem with multiple feasible solutions (i.e., hypotheses). This amplifies uncertainty and ambiguity in full-body motion estimation, especially for the lower-body joints. Therefore, we propose a new method, EnvPoser, that employs a two-stage framework to perform full-body motion estimation using sparse tracking signals and pre-scanned environment from VR devices. EnvPoser models the multi-hypothesis nature of human motion through an uncertainty-aware estimation module in the first stage. In the second stage, we refine these multi-hypothesis estimates by integrating semantic and geometric environmental constraints, ensuring that the final motion estimation aligns realistically with both the environmental context and physical interactions. Qualitative and quantitative experiments on two public datasets demonstrate that our method achieves state-of-the-art performance, highlighting significant improvements in human motion estimation within motion-environment interaction scenarios.