FacePoseNet: Making a Case for Landmark-Free Face Alignment (2017-08-24T00:00:00.000000Z)

TL;DR

The FacePoseNet (FPN) is claimed to be a far faster and far more accurate face alignment method than using facial landmark detectors, and aligns faces at a small fraction of the computational cost of comparably accurate landmark detectors.

Abstract

We show how a simple convolutional neural network (CNN) can be trained to accurately and robustly regress 6 degrees of freedom (6DoF) 3D head pose, directly from image intensities. We further explain how this FacePoseNet (FPN) can be used to align faces in 2D and 3D as an alternative to explicit facial landmark detection for these tasks. We claim that in many cases the standard means of measuring landmark detector accuracy can be misleading when comparing different face alignments. Instead, we compare our FPN with existing methods by evaluating how they affect face recognition accuracy on the IJB-A and IJB-B benchmarks: using the same recognition pipeline, but varying the face alignment method. Our results show that (a) better landmark detection accuracy measured on the 300W benchmark does not necessarily imply better face recognition accuracy. (b) Our FPN provides superior 2D and 3D face alignment on both benchmarks. Finally, (c), FPN aligns faces at a small fraction of the computational cost of comparably accurate landmark detectors. For many purposes, FPN is thus a far faster and far more accurate face alignment method than using facial landmark detectors.

Authors

G. Medioni

4 papers

R. Nevatia

9 papers

I. Masi

5 papers

TL;DR

Abstract

Authors

References57 items

IARPA Janus Benchmark-B Face Dataset

Rapid Synthesis of Massive Face Sets for Improved Face Recognition

L2-constrained Softmax Loss for Discriminative Face Verification

KEPLER: Keypoint and Pose Estimation of Unconstrained Faces by Learning Efficient H-CNN Regressors

Regressing Robust and Discriminative 3D Morphable Models with a Very Deep Neural Network

Convolutional Experts Constrained Local Model for Facial Landmark Detection

Deep Constrained Local Models for Facial Landmark Detection

Learning Detailed Face Reconstruction from a Single Image

An All-In-One Convolutional Neural Network for Face Analysis

ObjectNet3D: A Large Scale Database for 3D Object Recognition

Fast Single Shot Detection and Pose Estimation

A multi-scale cascade fully convolutional network face detector

Large-Pose Face Alignment via CNN-Based Dense 3D Model Fitting

Kernel ELM and CNN Based Facial Age Estimation

Pose-Aware Face Recognition in the Wild

Marr Revisited: 2D-3D Alignment via Surface Normal Prediction

Do We Really Need to Collect Millions of Faces for Effective Face Recognition?

Template Adaptation for Face Verification and Identification

OpenFace: An open source facial behavior analysis toolkit

300 Faces In-The-Wild Challenge: database and results

Deep Residual Learning for Image Recognition

Facial Landmark Detection with Tweaked Convolutional Neural Networks

Emotion Recognition in the Wild via Convolutional Neural Networks and Mapped Binary Patterns

Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A

Age and gender classification using convolutional neural networks

High-fidelity Pose and Expression Normalization for face recognition in the wild

Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views

Age and Gender Estimation of Unfiltered Faces

Effective face frontalization in unconstrained images

Deep Learning Face Attributes in the Wild

Improved Spatiotemporal Local Monogenic Binary Pattern for Emotion Recognition in The Wild

Cross-Age Reference Coding for Age-Invariant Face Recognition and Retrieval

Face Alignment at 3000 FPS via Regressing Local Binary Features

Incremental Face Alignment in the Wild

Beyond PASCAL: A benchmark for 3D object detection in the wild

Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition

300 Faces in-the-Wild Challenge: The First Facial Landmark Localization Challenge

Constrained Local Neural Fields for Robust Facial Landmark Detection in the Wild

Localizing Parts of Faces Using a Consensus of Exemplars

Viewing Real-World Faces in 3D

Robust Face Landmark Estimation under Occlusion

Supervised Descent Method and Its Applications to Face Alignment

Single View Depth Estimation from Examples

ImageNet classification with deep convolutional neural networks

Interactive Facial Feature Localization

Face Alignment by Explicit Shape Regression

Face detection, pose estimation, and landmark localization in the wild

Real-time facial feature detection using conditional regression forests

Annotated Facial Landmarks in the Wild: A large-scale, real-world database for facial landmark localization

Dlib-ml: A Machine Learning Toolkit

Unsupervised Joint Alignment of Complex Images

Face alignment across large poses: A 3D solution

Available www.

Deep Face Recognition

Objectnet 3 D : A large scale database for 3 D object recognition Beyond pascal : A benchmark for 3 D object detection in the wild

Viewing real - world faces in 3 D . In Proc . Int . Conf . Comput . Vision , pages 3607 – 3614 . IEEE ,

Noname manuscript No. (will be inserted by the editor) EPnP: An Accurate O(n) Solution to the PnP Problem

Field of Study

Journal Information

Name

Page