# 人脸对齐--How far are we from solving the 2D & 3D Face Alignment problem

How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks) ICCV2017 https://www.adrianbulat.com/face-alignment Pytorch Code: https://github.com/1adrianb/face-alignment Torch7 Code: https://github.com/1adrianb/2D-and-3D-face-alignment

facial landmark localization 也就是 face alignment

1 Introduction cascaded regression methods 在人脸对齐上取得不错的效果，但是当存在 large (and unfamiliar) facial poses（也就是一部分特征点 self-occluded landmarks or large in-plane rotations）cascaded regression methods 效果就不太好。近年来 fully Convolutional Neural Network architectures based on heatmap regression have revolutionized human pose estimation，于是沿着这个思路来做人脸对齐。

2 Closely related work 2D face alignment： 这里主要使用的是 cascaded regression 方法，基本解决可控人脸姿态的数据库 LFPW [2], Helen [22] and 300-W [30]

CNNs for face alignment：cascade CNN；multi-task learning；recurrent neural networks ；near-frontal faces of 300-W [30] large pose and 3D face alignment

Transferring landmark annotations 数据库的迁移学习

3 Datasets 当前 2D 3D 人脸对齐数据库的一些情况

3.3. Metrics 一般使用的度量方法是 the metric used for face alignment is the point-to-point Euclidean distance normalized by the interocular distance 这里我们改进了一下度量方式:normalize by the bounding box size. In particular, we used the Normalized Mean Error

4 Method 4.1. 2D and 3D Face Alignment Networks Face Alignment Network (FAN) 基于 Hour-Glass (HG) network of [23]

we used 300W-LP-2D and 300W-LP-3D to train 2D-FAN and 3D-FAN

4.2. 2D-to-3D Face Alignment Network 将2D 标记数据转为 3D 标记数据

4.3. Training 这要介绍了各个网络的训练

Conclusion： 2D-FAN achieves near saturating performance on the above 2D datasets

6 Large Scale 3D Faces in-the-Wild dataset 2D-to-3D FAN

2D 到3D 的转换引入一定的误差

7 3D face alignment

Facial pose is not a major issue for 3D-FAN

Resolution is not a major issue for 3D-FAN

Initialization is not a major issue for 3D-FAN

There is a moderate performance drop vs the number of parameters of 3D-FAN

0 条评论

## 相关文章

2152

3.1K12

### ResNet原理及其在TF-Slim中的实现

01 摘要 微软的深度残差网络ResNet源于2016年CVPR最佳论文---图像识别中的深度残差学习（Deep Residual Learning for I...

5417

### 用CNN做句子分类：CNN Sentence Classification (with Theano code)

01 Intro 本篇文章来细说CNN在NLP中的一大应用————句子分类。通过Yoon Kim的论文介绍一个应用，分析代码，并重构代码。 重构后的代码放在gi...

7345

7018

1.4K10

4194

35911

4934

4709