Face Alignment

28 papers with code · Computer Vision

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.

State-of-the-art leaderboards

Latest papers with code

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

18 Aug 2019thesouthfrog/stylealign

Facial landmark detection, or face alignment, is a fundamental task that has been extensively studied.

FACE ALIGNMENT FACIAL LANDMARK DETECTION

7
18 Aug 2019
207
22 Mar 2019

Face Alignment using a 3D Deeply-initialized Ensemble of Regression Trees

5 Feb 2019bobetocalo/bobetocalo_eccv18

In this paper we present 3DDE, a robust and efficient face alignment algorithm based on a coarse-to-fine cascade of ensembles of regression trees.

FACE ALIGNMENT

36
05 Feb 2019

Towards Highly Accurate and Stable Face Alignment for High-Resolution Videos

1 Nov 2018tyshiwo/FHR_alignment

In recent years, heatmap regression based models have shown their effectiveness in face alignment and pose estimation.

FACE ALIGNMENT POSE ESTIMATION QUANTIZATION

42
01 Nov 2018

On Learning 3D Face Morphable Model from In-the-wild Images

28 Aug 2018tranluan/Nonlinear_Face_3DMM

To address these problems, this paper proposes an innovative framework to learn a nonlinear 3DMM model from a large set of in-the-wild face images, without collecting 3D face scans.

3D RECONSTRUCTION FACE ALIGNMENT IMAGE GENERATION

268
28 Aug 2018

Hierarchical binary CNNs for landmark localization with limited resources

14 Aug 20181996scarlet/OpenVtuber

To this end, we make the following contributions: (a) we are the first to study the effect of neural network binarization on localization tasks, namely human pose estimation and face alignment.

FACE ALIGNMENT POSE ESTIMATION

6
14 Aug 2018

Quantized Densely Connected U-Nets for Efficient Landmark Localization

ECCV 2018 zhiqiangdon/CU-Net

Finally, to reduce the memory consumption and high precision operations both in training and testing, we further quantize weights, inputs, and gradients of our localization network to low bit-width numbers.

FACE ALIGNMENT POSE ESTIMATION

190
07 Aug 2018

Deep Multi-Center Learning for Face Alignment

5 Aug 2018ZhiwenShao/MCNet-Extension

Most of the existing deep learning methods only use one fully-connected layer called shape prediction layer to estimate the locations of facial landmarks.

FACE ALIGNMENT

11
05 Aug 2018

Look at Boundary: A Boundary-Aware Face Alignment Algorithm

CVPR 2018 zhusz/CVPR15-CFSS

By utilising boundary information of 300-W dataset, our method achieves 3. 92% mean error with 0. 39% failure rate on COFW dataset, and 1. 25% mean error on AFLW-Full dataset.

#4 best model for Face Alignment on 300W

FACE ALIGNMENT

151
26 May 2018