Look at Boundary: A Boundary-Aware Face Alignment Algorithm

by   Wayne Wu, et al.

We present a novel boundary-aware face alignment algorithm by utilising boundary lines as the geometric structure of a human face to help facial landmark localisation. Unlike the conventional heatmap based method and regression based method, our approach derives face landmarks from boundary lines which remove the ambiguities in the landmark definition. Three questions are explored and answered by this work: 1. Why using boundary? 2. How to use boundary? 3. What is the relationship between boundary estimation and landmarks localisation? Our boundary- aware face alignment algorithm achieves 3.49 error on 300-W Fullset, which outperforms state-of-the-art methods by a large margin. Our method can also easily integrate information from other datasets. By utilising boundary information of 300-W dataset, our method achieves 3.92 mean error with 0.39 AFLW-Full dataset. Moreover, we propose a new dataset WFLW to unify training and testing across different factors, including poses, expressions, illuminations, makeups, occlusions, and blurriness. Dataset and model will be publicly available at https://wywu.github.io/projects/LAB/LAB.html


page 1

page 3

page 4


Think about boundary: Fusing multi-level boundary information for landmark heatmap regression

Although current face alignment algorithms have obtained pretty good per...

PropagationNet: Propagate Points to Curve to Learn Structure Information

Deep learning technique has dramatically boosted the performance of face...

ReenactGAN: Learning to Reenact Faces via Boundary Transfer

We present a novel learning-based framework for face reenactment. The pr...

LDDMM-Face: Large Deformation Diffeomorphic Metric Learning for Flexible and Consistent Face Alignment

We innovatively propose a flexible and consistent face alignment framewo...

Faster Than Real-time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Poses

Facial alignment involves finding a set of landmark points on an image w...

Transferring Landmark Annotations for Cross-Dataset Face Alignment

Dataset bias is a well known problem in object recognition domain. This ...

Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Translation

Facial landmark detection, or face alignment, is a fundamental task that...

Code Repositories


Code for "Look at Boundary: A Boundary-Aware Face Alignment Algorithm"

view repo