Papers › On the Calibration of Human Pose Estimation
On the Calibration of Human Pose Estimation
Kerui Gu, Rongyu Chen, Angela Yao
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Pose Estimation | COCO test-dev | CCNet (ViTPose) | AP | - | #47 of 47 | Archive leaderboard | report |
| Pose Estimation | COCO test-dev | CCNet (ViTPose) | AP50 | - | #47 of 47 | Archive leaderboard | report |
| Pose Estimation | COCO test-dev | CCNet (ViTPose) | AP75 | - | #47 of 47 | Archive leaderboard | report |
| Pose Estimation | COCO test-dev | CCNet (ViTPose) | APL | - | #47 of 47 | Archive leaderboard | report |
| Pose Estimation | COCO test-dev | CCNet (ViTPose) | APM | - | #47 of 47 | Archive leaderboard | report |
| Pose Estimation | COCO test-dev | CCNet (ViTPose) | AR | - | #47 of 47 | Archive leaderboard | report |
| Pose Estimation | COCO val2017 | CCNet (ViTPose-B_GT-bbox_256x192) | AP | 78.1 | #1 of 11 | Archive leaderboard | report |
| Pose Estimation | COCO val2017 | CCNet (ViTPose-B_GT-bbox_256x192) | AP50 | 93.7 | #1 of 11 | Archive leaderboard | report |
| Pose Estimation | COCO val2017 | CCNet (ViTPose-B_GT-bbox_256x192) | AP75 | 85.0 | #1 of 11 | Archive leaderboard | report |
| Pose Estimation | COCO val2017 | CCNet (ViTPose-B_GT-bbox_256x192) | AR | 80.4 | #1 of 11 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections