Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Shipeng, Xiong, Ziliang, Wandt, Bastian, Forssén, Per-Erik
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917231757099008
author Liu, Shipeng
Xiong, Ziliang
Wandt, Bastian
Forssén, Per-Erik
author_facet Liu, Shipeng
Xiong, Ziliang
Wandt, Bastian
Forssén, Per-Erik
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_02287
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation
Liu, Shipeng
Xiong, Ziliang
Wandt, Bastian
Forssén, Per-Erik
Computer Vision and Pattern Recognition
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.
title Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.02287