Probablistic Restoration with Adaptive Noise Sampling for 3D Human Pose Estimation

TL;DR

This paper introduces PRPose, a probabilistic framework that enhances 3D human pose estimation by efficiently generating multiple hypotheses through adaptive noise sampling, improving robustness without heavy generative models.

Contribution

It presents a lightweight, weakly supervised probabilistic approach for multi-hypothesis 3D pose estimation that is compatible with single-hypothesis models, reducing computational costs.

Findings

Outperforms existing methods on Human3.6M and MPI-INF-3DHP benchmarks.

Demonstrates improved robustness and efficiency in 3D pose estimation.

Effective integration with lightweight single-hypothesis models.

Abstract

The accuracy and robustness of 3D human pose estimation (HPE) are limited by 2D pose detection errors and 2D to 3D ill-posed challenges, which have drawn great attention to Multi-Hypothesis HPE research. Most existing MH-HPE methods are based on generative models, which are computationally expensive and difficult to train. In this study, we propose a Probabilistic Restoration 3D Human Pose Estimation framework (PRPose) that can be integrated with any lightweight single-hypothesis model. Specifically, PRPose employs a weakly supervised approach to fit the hidden probability distribution of the 2D-to-3D lifting process in the Single-Hypothesis HPE model and then reverse-map the distribution to the 2D pose input through an adaptive noise sampling strategy to generate reasonable multi-hypothesis samples effectively. Extensive experiments on 3D HPE benchmarks (Human3.6M and MPI-INF-3DHP) highlight the effectiveness and efficiency of PRPose. Code is available at: https://github.com/xzhouzeng/PRPose.