# On the Calibration of Human Pose Estimation

arXiv: https://arxiv.org/abs/2311.17105 · HTML: https://mlsanity.com/paper/2311.17105/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 40 references that are in the map.
- First posted on arXiv 28 Nov 2023.

## Builds on (most cited first, 30 of 31)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [Deep Evidential Regression](https://mlsanity.com/paper/1910.02600/) (2019)
- [DeepPose: Human Pose Estimation via Deep Neural Networks](https://mlsanity.com/paper/1312.4659/) (2013)
- [Integral Human Pose Regression](https://mlsanity.com/paper/1711.08229/) (2017)
- [Addressing Failure Prediction by Learning Model Confidence](https://mlsanity.com/paper/1910.04851/) (2019)
- [Whole-Body Human Pose Estimation in the Wild](https://mlsanity.com/paper/2007.11858/) (2020)
- [Distribution-Aware Coordinate Representation for Human Pose Estimation](https://mlsanity.com/paper/1910.06278/) (2019)
- [Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow](https://mlsanity.com/paper/1802.07095/) (2018)
- [Towards Accurate Multi-person Pose Estimation in the Wild](https://mlsanity.com/paper/1701.01779/) (2017)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [Pose Recognition with Cascade Transformers](https://mlsanity.com/paper/2104.06976/) (2021)
- [Distribution Calibration for Regression](https://mlsanity.com/paper/1905.06023/) (2019)
- [Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows](https://mlsanity.com/paper/2107.13788/) (2021)
- [Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation](https://mlsanity.com/paper/2007.02846/) (2020)
- [Benchmarking and Error Diagnosis in Multi-Instance Pose Estimation](https://mlsanity.com/paper/1707.05388/) (2017)
- [Poseur: Direct Human Pose Regression with Transformers](https://mlsanity.com/paper/2201.07412/) (2022)
- [Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence](https://mlsanity.com/paper/2104.08736/) (2021)
- [Calibrated and Sharp Uncertainties in Deep Learning via Density Estimation](https://mlsanity.com/paper/2112.07184/) (2021)
- [MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks](https://mlsanity.com/paper/2203.01437/) (2022)
- [Multiclass Confidence and Localization Calibration for Object Detection](https://mlsanity.com/paper/2306.08271/) (2023)
- [SLURP: Side Learning Uncertainty for Regression Problems](https://mlsanity.com/paper/2110.11182/) (2021)
- [Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression](https://mlsanity.com/paper/2308.09065/) (2023)

## Built on by (most cited first, 10 of 10)

- [ProbPose: A Probabilistic Approach to 2D Human Pose Estimation](https://mlsanity.com/paper/2412.02254/) (2024)
- [KITRO: Refining Human Mesh by 2D Clues and Kinematic-tree Rotation](https://mlsanity.com/paper/2405.19833/) (2024)
- [Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery](https://mlsanity.com/paper/2411.16289/) (2024)
- [Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation](https://mlsanity.com/paper/2403.06164/) (2024)
- [Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle](https://mlsanity.com/paper/2412.01562/) (2024)
- [Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation](https://mlsanity.com/paper/2505.02287/) (2025)
- [Flow Matching for Probabilistic Monocular 3D Human Pose Estimation](https://mlsanity.com/paper/2601.16763/) (2026)
- [Semantics-aware Test-time Adaptation for 3D Human Pose Estimation](https://mlsanity.com/paper/2502.10724/) (2025)
- [Online Test-time Adaptation for 3D Human Pose Estimation: A Practical Perspective with Estimated 2D Poses](https://mlsanity.com/paper/2503.11194/) (2025)
- [MEOM: Multi-View Expected-OKS Maximization for Human Pose Triangulation](https://mlsanity.com/paper/2608.30521/) (2026)

## Abstract (arXiv)

Most 2D human pose estimation frameworks estimate keypoint confidence in an ad-hoc manner, using heuristics such as the maximum value of heatmaps. The confidence is part of the evaluation scheme, e.g., AP for the MSCOCO dataset, yet has been largely overlooked in the development of state-of-the-art methods. This paper takes the first steps in addressing miscalibration in pose estimation. From a calibration point of view, the confidence should be aligned with the pose accuracy. In practice, existing methods are poorly calibrated. We show, through theoretical analysis, why a miscalibration gap exists and how to narrow the gap. Simply predicting the instance size and adjusting the confidence function gives considerable AP improvements. Given the black-box nature of deep neural networks, however, it is not possible to fully close this gap with only closed-form adjustments. As such, we go one step further and learn network-specific adjustments by enforcing consistency between confidence and pose accuracy. Our proposed Calibrated ConfidenceNet (CCNet) is a light-weight post-hoc addition that improves AP by up to 1.4% on off-the-shelf pose estimation frameworks. Applied to the downstream task of mesh recovery, CCNet facilitates an additional 1.0mm decrease in 3D keypoint error.