Papers › On the representation and methodology for wide and short range head pose estimation
On the representation and methodology for wide and short range head pose estimation
Alejandro Cobo, Roberto Valle, José M. Buenaposada, Luis Baumela
Head pose estimation (HPE) is a problem of interest in computer vision to improve the performance of face processing tasks in semi-frontal or profile settings. Recent applications require the analysis of faces in the full 360{\deg} rotation range. Traditional approaches to solve the semi-frontal and profile cases are not directly amenable for the full rotation case. In this paper we analyze the methodology for short- and wide-range HPE and discuss which representations and metrics are adequate for each case. We show that the popular Euler angles representation is a good choice for short-range HPE, but not at extreme rotations. However, the Euler angles' gimbal lock problem prevents them from being used as a valid metric in any setting. We also revisit the current cross-data set evaluation methodology and note that the lack of alignment between the reference systems of the training and test data sets negatively biases the results of all articles in the literature. We introduce a procedure to quantify this misalignment and a new methodology for cross-data set HPE that establishes new, more accurate, SOTA for the 300W-LP|Biwi benchmark. We also propose a generalization of the geodesic angular distance metric that enables the construction of a loss that controls the contribution of each training sample to the optimization of the model. Finally, we introduce a wide range HPE benchmark based on the CMU Panoptic data set.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
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 |
|---|---|---|---|---|---|---|---|
| Head Pose Estimation | AFLW2000 | SRHP-Euler | Geodesic Error (GE) | 5.29 | #2 of 25 | Archive leaderboard | report |
| Head Pose Estimation | AFLW2000 | SRHP-Euler | MAE | 3.25 | #2 of 25 | Archive leaderboard | report |
| Head Pose Estimation | AFLW2000 | SRHP-6D | Geodesic Error (GE) | 5.37 | #5 of 25 | Archive leaderboard | report |
| Head Pose Estimation | AFLW2000 | SRHP-6D | MAE | 3.49 | #5 of 25 | Archive leaderboard | report |
| Head Pose Estimation | BIWI | SRHP-6D | Geodesic Error (GE) | 7.30 | #12 of 29 | Archive leaderboard | report |
| Head Pose Estimation | BIWI | SRHP-6D | Geodesic Error - aligned (GE) | 5.48 | #12 of 29 | Archive leaderboard | report |
| Head Pose Estimation | BIWI | SRHP-6D | MAE (trained with other data) | 3.98 | #12 of 29 | Archive leaderboard | report |
| Head Pose Estimation | BIWI | SRHP-6D | MAE-aligned (trained with other data) | 3.21 | #12 of 29 | Archive leaderboard | report |
| Head Pose Estimation | BIWI | SRHP-Euler | Geodesic Error (GE) | 7.49 | #14 of 29 | Archive leaderboard | report |
| Head Pose Estimation | BIWI | SRHP-Euler | Geodesic Error - aligned (GE) | 5.42 | #14 of 29 | Archive leaderboard | report |
| Head Pose Estimation | BIWI | SRHP-Euler | MAE (trained with other data) | 4.13 | #14 of 29 | Archive leaderboard | report |
| Head Pose Estimation | BIWI | SRHP-Euler | MAE-aligned (trained with other data) | 3.16 | #14 of 29 | Archive leaderboard | report |
| Head Pose Estimation | Panoptic | WRHP-6D-Opal | Geodesic Error (GE) | 7.45 | #1 of 6 | Archive leaderboard | report |
| Head Pose Estimation | Panoptic | WRHP-6D | Geodesic Error (GE) | 7.70 | #2 of 6 | Archive leaderboard | report |
| Head Pose Estimation | Panoptic | WRHP-Quaternion | Geodesic Error (GE) | 9.32 | #4 of 6 | Archive leaderboard | report |
| Head Pose Estimation | Panoptic | WRHP-Euler | Geodesic Error (GE) | 10.47 | #5 of 6 | 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