3D Dense Face Alignment via Graph Convolution Networks

2019/04/11 by Huawei Wei, Shuang Liang, Wei, Huawei +3 · 1 citation
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face recognition and analysis #Generative Adversarial Networks and Image Synthesis #Video Surveillance and Tracking Methods

paper · pdf · doi:10.48550/arxiv.1904.05562

openalex publication_date 2019/04/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recently, 3D face reconstruction and face alignment tasks are gradually combined into one task: 3D dense face alignment. Its goal is to reconstruct the 3D geometric structure of face with pose information. In this paper, we propose a graph convolution network to regress 3D face coordinates. Our method directly performs feature learning on the 3D face mesh, where the geometric structure and details are well preserved. Extensive experiments show that our approach gains superior performance over state-of-the-art methods on several challenging datasets.

Citations

• Adam: A Method for Stochastic Optimization
• Laplacian matrices of graphs: a survey
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Semi-Supervised Classification with Graph Convolutional Networks
• Geometric Deep Learning: Going beyond Euclidean data

Cited by

• Balanced Alignment for Face Recognition: A Joint Learning Approach

Related

• 3D Dense Face Alignment with Fused Features by Aggregating CNNs and GCNs
• Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network
• CSANet: Channel Spatial Attention Network for Robust 3D Face Alignment and Reconstruction
• 3D Face Alignment Through Fusion of Head Pose Information and Features
• Dense Face Alignment