Papers › img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation
img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation
Vítor Albiero, Xingyu Chen, Xi Yin, Guan Pang, Tal Hassner
We propose real-time, six degrees of freedom (6DoF), 3D face pose estimation without face detection or landmark localization. We observe that estimating the 6DoF rigid transformation of a face is a simpler problem than facial landmark detection, often used for 3D face alignment. In addition, 6DoF offers more information than face bounding box labels. We leverage these observations to make multiple contributions: (a) We describe an easily trained, efficient, Faster R-CNN--based model which regresses 6DoF pose for all faces in the photo, without preliminary face detection. (b) We explain how pose is converted and kept consistent between the input photo and arbitrary crops created while training and evaluating our model. (c) Finally, we show how face poses can replace detection bounding box training labels. Tests on AFLW2000-3D and BIWI show that our method runs at real-time and outperforms state of the art (SotA) face pose estimators. Remarkably, our method also surpasses SotA models of comparable complexity on the WIDER FACE detection benchmark, despite not been optimized on bounding box labels.
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 |
|---|---|---|---|---|---|---|---|
| Face Detection | WIDER Face (Easy) | img2pose | AP | 0.9 | #24 of 27 | Archive leaderboard | report |
| Face Detection | WIDER Face (Hard) | img2pose | AP | 0.839 | #24 of 40 | Archive leaderboard | report |
| Face Detection | WIDER Face (Medium) | img2pose | AP | 0.890 | #27 of 37 | Archive leaderboard | report |
| Head Pose Estimation | AFLW2000 | img2pose | Geodesic Error (GE) | 6.41 | #10 of 25 | Archive leaderboard | report |
| Head Pose Estimation | AFLW2000 | img2pose | MAE | 3.913 | #10 of 25 | Archive leaderboard | report |
| Head Pose Estimation | AFLW2000 | img2pose | MAE_t | 0.099 | #10 of 25 | Archive leaderboard | report |
| Head Pose Estimation | AFLW2000 | RetinaFace R-50 (5 points) | MAE | 4.839 | #16 of 25 | Archive leaderboard | report |
| Head Pose Estimation | AFLW2000 | RetinaFace R-50 (5 points) | MAE_t | 0.114 | #16 of 25 | Archive leaderboard | report |
| Head Pose Estimation | BIWI | img2pose | Geodesic Error (GE) | 7.10 | #10 of 29 | Archive leaderboard | report |
| Head Pose Estimation | BIWI | img2pose | Geodesic Error - aligned (GE) | 6.23 | #10 of 29 | Archive leaderboard | report |
| Head Pose Estimation | BIWI | img2pose | MAE (trained with other data) | 3.786 | #10 of 29 | Archive leaderboard | report |
| Head Pose Estimation | BIWI | img2pose | MAE-aligned (trained with other data) | 3.4 | #10 of 29 | Archive leaderboard | report |
| Head Pose Estimation | BIWI | RetinaFace R-50 (5 points) | MAE (trained with other data) | 4.578 | #17 of 29 | 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.
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