Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation
This work addresses uncertainty-aware human pose estimation for applications like virtual reality and motion analysis, representing an incremental improvement over existing methods.
The paper tackled the problem of balancing accuracy, computational efficiency, and reliable uncertainty quantification in human pose estimation by proposing Continuous Flow Residual Estimation (CFRE), which integrates Continuous Normalizing Flows into regression-based models, resulting in better accuracy and uncertainty quantification with retained computational efficiency on 2D and 3D tasks.
Human Pose Estimation (HPE) is increasingly important for applications like virtual reality and motion analysis, yet current methods struggle with balancing accuracy, computational efficiency, and reliable uncertainty quantification (UQ). Traditional regression-based methods assume fixed distributions, which might lead to poor UQ. Heatmap-based methods effectively model the output distribution using likelihood heatmaps, however, they demand significant resources. To address this, we propose Continuous Flow Residual Estimation (CFRE), an integration of Continuous Normalizing Flows (CNFs) into regression-based models, which allows for dynamic distribution adaptation. Through extensive experiments, we show that CFRE leads to better accuracy and uncertainty quantification with retained computational efficiency on both 2D and 3D human pose estimation tasks.