Probablistic Restoration with Adaptive Noise Sampling for 3D Human Pose Estimation
This work addresses robustness and computational cost issues in 3D human pose estimation for applications like motion capture and human-computer interaction, offering an incremental improvement over existing multi-hypothesis methods.
The paper tackles the problem of 3D human pose estimation by proposing a probabilistic restoration framework (PRPose) that integrates with lightweight single-hypothesis models to generate multi-hypothesis samples, achieving improved accuracy and efficiency on benchmarks like Human3.6M and MPI-INF-3DHP.
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.