Pose-Invariant 3D Face Alignment

Abstract

Face alignment aims to estimate the locations of a set of landmarks for a given image. This problem has received much attention as evidenced by the recent advancement in both the methodology and performance. However, most of the existing works neither explicitly handle face images with arbitrary poses, nor perform large-scale experiments on non-frontal and profile face images. In order to address these limitations, this paper proposes a novel face alignment algorithm that estimates both 2D and 3D landmarks and their 2D visibilities for a face image with an arbitrary pose. By integrating a 3D deformable model, a cascaded coupled-regressor approach is designed to estimate both the camera projection matrix and the 3D landmarks. Furthermore, the 3D model also allows us to automatically estimate the 2D landmark visibilities via surface normals. We gather a substantially larger collection of all-pose face images to evaluate our algorithm and demonstrate superior performances than the state-of-the-art methods.

References in corpus (2)

• Face Expression Recognition and Analysis: The State of the Art
• Facial Feature Point Detection: A Comprehensive Survey

Cited by in corpus (16)

• Facial Landmark Detection: a Literature Survey
• Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network
• Towards Large-Pose Face Frontalization in the Wild
• An Empirical Study of Recent Face Alignment Methods
• Pose-Invariant Face Alignment with a Single CNN
• Deep Learning For Face Recognition: A Critical Analysis
• Nonlinear 3D Face Morphable Model
• GoDP: Globally optimized dual pathway system for facial landmark localization in-the-wild
• Simultaneous Facial Landmark Detection, Pose and Deformation Estimation under Facial Occlusion
• Learning Dense Facial Correspondences in Unconstrained Images
• On 3D Face Reconstruction via Cascaded Regression in Shape Space
• Landmark Weighting for 3DMM Shape Fitting
• A Fast and Accurate System for Face Detection, Identification, and Verification
• A Convolution Tree with Deconvolution Branches: Exploiting Geometric Relationships for Single Shot Keypoint Detection
• Deep Face Feature for Face Alignment
• Multilevel active registration for kinect human body scans: from low quality to high quality