Face Alignment
100 papers with code • 26 benchmarks • 17 datasets
Face alignment is the task of identifying the geometric structure of faces in digital images, and attempting to obtain a canonical alignment of the face based on translation, scale, and rotation.
( Image credit: 3DDFA_V2 )
Benchmarks
These leaderboards are used to track progress in Face Alignment
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Face Alignment models and implementations
CelebA
300W
Helen
AFLW
AFW
LFPW
AFLW2000-3D
COFW
WFLW
FaceScape
Most implemented papers
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
Face detection and alignment in unconstrained environment are challenging due to various poses, illuminations and occlusions.
Deep High-Resolution Representation Learning for Visual Recognition
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection.
High-Resolution Representations for Labeling Pixels and Regions
leoxiaobin/deep-high-resolution-net.pytorch
•
•
The proposed approach achieves superior results to existing single-model networks on COCO object detection.
PFLD: A Practical Facial Landmark Detector
Being accurate, efficient, and compact is essential to a facial landmark detector for practical use.
Fine-Grained Head Pose Estimation Without Keypoints
natanielruiz/deep-head-pose
•
•
Estimating the head pose of a person is a crucial problem that has a large amount of applications such as aiding in gaze estimation, modeling attention, fitting 3D models to video and performing face alignment.
Learning a model of facial shape and expression from 4D scans
Rubikplayer/flame-fitting
•
•
SIGGRAPH Asia 2017
FLAME is low-dimensional but more expressive than the FaceWarehouse model and the Basel Face Model.
RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild
serengil/deepface
•
•
CVPR 2020
Though tremendous strides have been made in uncontrolled face detection, accurate and efficient 2D face alignment and 3D face reconstruction in-the-wild remain an open challenge.
How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)
1adrianb/face-alignment
•
•
ICCV 2017
To this end, we make the following 5 contributions: (a) we construct, for the first time, a very strong baseline by combining a state-of-the-art architecture for landmark localization with a state-of-the-art residual block, train it on a very large yet synthetically expanded 2D facial landmark dataset and finally evaluate it on all other 2D facial landmark datasets.
ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging
In this paper, we present an attention-guided deformable convolutional network for hand-held multi-frame high dynamic range (HDR) imaging, namely ADNet.
Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression
protossw512/AdaptiveWingLoss
•
•
ICCV 2019
Then we propose a novel loss function, named Adaptive Wing loss, that is able to adapt its shape to different types of ground truth heatmap pixels.
