Face Alignment Across Large Poses: A 3D Solution
arXiv:1511.07212 · doi:10.1109/TPAMI.2017.2778152
Abstract
Face alignment, which fits a face model to an image and extracts the semantic meanings of facial pixels, has been an important topic in CV community. However, most algorithms are designed for faces in small to medium poses (below 45 degree), lacking the ability to align faces in large poses up to 90 degree. The challenges are three-fold: Firstly, the commonly used landmark-based face model assumes that all the landmarks are visible and is therefore not suitable for profile views. Secondly, the face appearance varies more dramatically across large poses, ranging from frontal view to profile view. Thirdly, labelling landmarks in large poses is extremely challenging since the invisible landmarks have to be guessed. In this paper, we propose a solution to the three problems in an new alignment framework, called 3D Dense Face Alignment (3DDFA), in which a dense 3D face model is fitted to the image via convolutional neutral network (CNN). We also propose a method to synthesize large-scale training samples in profile views to solve the third problem of data labelling. Experiments on the challenging AFLW database show that our approach achieves significant improvements over state-of-the-art methods.
11 pages, 10 figures
References in corpus (3)
Cited by in corpus (49)
- On Learning 3D Face Morphable Model from In-the-wild Images
- PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images
- Face Forgery Detection by 3D Decomposition
- Multi-task head pose estimation in-the-wild
- Face Alignment using a 3D Deeply-initialized Ensemble of Regression Trees
- An End-to-End Review of Gaze Estimation and its Interactive Applications on Handheld Mobile Devices
- Towards 3D Face Reconstruction in Perspective Projection: Estimating 6DoF Face Pose from Monocular Image
- Towards Fast, Accurate and Stable 3D Dense Face Alignment
- LAEO-Net++: revisiting people Looking At Each Other in videos
- Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images
- On the representation and methodology for wide and short range head pose estimation
- Rank-based verification for long-term face tracking in crowded scenes
- AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detection
- Facial UV Map Completion for Pose-invariant Face Recognition: A Novel Adversarial Approach based on Coupled Attention Residual UNets
- Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape
- End-to-end Hand Mesh Recovery from a Monocular RGB Image
- Weakly-Supervised Multi-Face 3D Reconstruction
- FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction
- Static and Dynamic Fusion for Multi-modal Cross-ethnicity Face Anti-spoofing
- Face Detection with Feature Pyramids and Landmarks
- Cross-modal Deep Face Normals with Deactivable Skip Connections
- VRMM: A Volumetric Relightable Morphable Head Model
- Frankenstein: Learning Deep Face Representations using Small Data
- CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing
- RankPose: Learning Generalised Feature with Rank Supervision for Head Pose Estimation
- Improving Face Anti-Spoofing by 3D Virtual Synthesis
- Real-time Memory Efficient Large-pose Face Alignment via Deep Evolutionary Network
- Expression-preserving face frontalization improves visually assisted speech processing
- Neural 3D Clothes Retargeting from a Single Image
- Task-agnostic Temporally Consistent Facial Video Editing
- Joint Face Detection and Facial Motion Retargeting for Multiple Faces
- Adversarial Relighting Against Face Recognition
- Face Frontalization Based on Robustly Fitting a Deformable Shape Model to 3D Landmarks
- Face Inverse Rendering via Hierarchical Decoupling
- Semantic Alignment: Finding Semantically Consistent Ground-truth for Facial Landmark Detection
- Gaussian Vector: An Efficient Solution for Facial Landmark Detection
- High-fidelity Face Tracking for AR/VR via Deep Lighting Adaptation
- Unsupervised Facial Action Unit Intensity Estimation via Differentiable Optimization
- Unsupervised Performance Analysis of 3D Face Alignment with a Statistically Robust Confidence Test
- Impact of facial landmark localization on facial expression recognition
- Towards Pose-invariant Lip-Reading
- A 3D model-based approach for fitting masks to faces in the wild
- Learning Robust 3D Face Reconstruction and Discriminative Identity Representation
- UniFaceGAN: A Unified Framework for Temporally Consistent Facial Video Editing
- A fast online cascaded regression algorithm for face alignment
- Separable Batch Normalization for Robust Facial Landmark Localization with Cross-protocol Network Training
- Towards Fine-grained 3D Face Dense Registration: An Optimal Dividing and Diffusing Method
- A Human Ear Reconstruction Autoencoder
- Is Complete Labeling Necessary? Understanding Active Learning in Longitudinal Medical Imaging