mlsanityData to 14 Oct 2026

Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation

arXiv 2505.02287 ↗First posted 4 May 2025cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 27 of its 30 references that are in the map. First posted on arXiv 4 May 2025.

Builds on

27 of 30 references.

References · 27

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2017Mask R-CNNcited by 7,277
  3. 2022Flow Matching for Generative Modelingcited by 5,702
  4. 2018Neural Ordinary Differential Equationscited by 3,779
  5. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  6. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  7. 2019Objects as Pointscited by 1,175
  8. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  9. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 594
  10. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  11. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  12. 2015Deep multi-scale video prediction beyond mean square errorcited by 300
15 more
  1. 2017Integral Human Pose Regressioncited by 256
  2. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 212
  3. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  4. 2018Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flowcited by 135
  5. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  6. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  7. 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
  8. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  9. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  10. 2021Pose Recognition with Cascade Transformerscited by 99
  11. 2019Single-Stage Multi-Person Pose Machinescited by 95
  12. 2020Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimationcited by 57
  13. 2024Uncertainty Quantification Metrics for Deep Regressioncited by 16
  14. 2023On the Calibration of Human Pose Estimationcited by 10
  15. 2020EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfercited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Uncertainty Propagation Networks for Neural Ordinary Differential Equationscited by 1
  2. 2026You Only Flow Once: Calibrated and Real-Time Radar Pose Estimation with Multi-Hypothesis Normalizing Flowscited by 0