Papers › Face Alignment Across Large Poses: A 3D Solution
Face Alignment Across Large Poses: A 3D Solution
Xiangyu Zhu, Zhen Lei, Xiaoming Liu, Hailin Shi, Stan Z. Li
Face alignment, which fits a face model to an image and extracts the semantic meanings of facial pixels, has been an important topic in CV community. However, most algorithms are designed for faces in small to medium poses (below 45 degree), lacking the ability to align faces in large poses up to 90 degree. The challenges are three-fold: Firstly, the commonly used landmark-based face model assumes that all the landmarks are visible and is therefore not suitable for profile views. Secondly, the face appearance varies more dramatically across large poses, ranging from frontal view to profile view. Thirdly, labelling landmarks in large poses is extremely challenging since the invisible landmarks have to be guessed. In this paper, we propose a solution to the three problems in an new alignment framework, called 3D Dense Face Alignment (3DDFA), in which a dense 3D face model is fitted to the image via convolutional neutral network (CNN). We also propose a method to synthesize large-scale training samples in profile views to solve the third problem of data labelling. Experiments on the challenging AFLW database show that our approach achieves significant improvements over state-of-the-art methods.
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
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Face Reconstruction | AFLW2000-3D | 3DDFA | Mean NME | 5.3695% | #6 of 8 | Archive leaderboard | report |
| 3D Face Reconstruction | Florence | 3DDFA | Mean NME | 6.3833% | #3 of 16 | Archive leaderboard | report |
| Face Alignment | AFLW2000 | 3DDFA | Error rate | 5.42 | #4 of 5 | Archive leaderboard | report |
| Face Alignment | AFLW2000-3D | 3DDFA + SDM | Balanced NME (2D Sparse Alignment) | 4.94% | #13 of 14 | Archive leaderboard | report |
| Facial Landmark Detection | 300W | CFSS | NME | 5.76 | #12 of 15 | Archive leaderboard | report |
| Facial Landmark Detection | 300W | 3DDFA | NME | 7.01 | #14 of 15 | Archive leaderboard | report |
| Head Pose Estimation | AFLW2000 | 3DDFA | MAE | 7.393 | #23 of 25 | Archive leaderboard | report |
| Head Pose Estimation | BIWI | 3DDFA | MAE (trained with other data) | 19.068 | #21 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