Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation
By: Shipeng Liu , Ziliang Xiong , Bastian Wandt and more
Potential Business Impact:
Lets computers understand body movements better.
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.
Similar Papers
Contrastive Normalizing Flows for Uncertainty-Aware Parameter Estimation
Data Analysis, Statistics and Probability
Finds hidden clues in science data.
Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows
Machine Learning (CS)
Shows how sure a computer is about its guesses.
FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation
CV and Pattern Recognition
Makes computers understand body poses better and faster.