Towards Fast, Accurate and Stable 3D Dense Face Alignment

2020/09/21 by Jianzhu Guo, Guo, Jianzhu, Xiangyu Zhu +9 · 13 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face and Expression Recognition #Face recognition and analysis #Video Surveillance and Tracking Methods

paper · pdf · doi:10.48550/arxiv.2009.09960

openalex publication_date 2020/09/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Existing methods of 3D dense face alignment mainly concentrate on accuracy, thus limiting the scope of their practical applications. In this paper, we propose a novel regression framework named 3DDFA-V2 which makes a balance among speed, accuracy and stability. Firstly, on the basis of a lightweight backbone, we propose a meta-joint optimization strategy to dynamically regress a small set of 3DMM parameters, which greatly enhances speed and accuracy simultaneously. To further improve the stability on videos, we present a virtual synthesis method to transform one still image to a short-video which incorporates in-plane and out-of-plane face moving. On the premise of high accuracy and stability, 3DDFA-V2 runs at over 50fps on a single CPU core and outperforms other state-of-the-art heavy models simultaneously. Experiments on several challenging datasets validate the efficiency of our method. Pre-trained models and code are available at https://github.com/cleardusk/3DDFA_V2.

Citations

• Face Alignment in Full Pose Range: A 3D Total Solution
• Learning a High Fidelity Pose Invariant Model for High-resolution Face\n Frontalization

Cited by

• Attack-Aware Deepfake Detection under Counter-Forensic Manipulations
• GRAPE: Graduated Routing for Articulated Portrait mesh Estimation
• Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image
• Bitbox: Behavioral Imaging Toolbox for Computational Analysis of Behavior from Videos
• FIELDS: Face reconstruction with accurate Inference of Expression using Learning with Direct Supervision
• Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark
• GLVD: Guided Learned Vertex Descent
• MSMA: Multi-Scale Feature Fusion For Multi-Attribute 3D Face Reconstruction From Unconstrained Images
• Hierarchical MLANet: Multi-level Attention for 3D Face Reconstruction From Single Images
• WEBEYETRACK: Scalable Eye-Tracking for the Browser via On-Device Few-Shot Personalization
• Geometry-Aware Video Inpainting for Joint Headset Occlusion Removal and Face Reconstruction in Social XR
• Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generation
• FLUX-Makeup: High-Fidelity, Identity-Consistent, and Robust Makeup Transfer via Diffusion Transformer

Related

• DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment
• Face Alignment in Full Pose Range: A 3D Total Solution
• Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network
• Dense Face Alignment
• Realistic face animation generation from videos