Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network

Yao Feng, Fan Wu, Xiaohu Shao, Yanfeng Wang, Xi Zhou
3/21/2018
cs.CVcs.GR

Official code: yfeng95/PRNet (5,022 stars, MIT, last commit 2022-07-25).

Abstract

We propose a straightforward method that simultaneously reconstructs the 3D facial structure and provides dense alignment. To achieve this, we design a 2D representation called UV position map which records the 3D shape of a complete face in UV space, then train a simple Convolutional Neural Network to regress it from a single 2D image. We also integrate a weight mask into the loss function during training to improve the performance of the network. Our method does not rely on any prior face model, and can reconstruct full facial geometry along with semantic meaning. Meanwhile, our network is very light-weighted and spends only 9.8ms to process an image, which is extremely faster than previous works. Experiments on multiple challenging datasets show that our method surpasses other state-of-the-art methods on both reconstruction and alignment tasks by a large margin.

View on arXivView PDF

Code Implementations(1)

yfeng95/PRNetOfficial100%
MIT

Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network (ECCV 2018)

5,022932PythonMar 20, 20184 years agoMIT
3dalignmentfacereconstructionswap

Similar Papers

3D Face Alignment Through Fusion of Head Pose Information and Features

87% match2023

DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment

87% match1 repo772023

Towards Fast, Accurate and Stable 3D Dense Face Alignment

85% match2 repos3.7k2020

Face Alignment in Full Pose Range: A 3D Total Solution

85% match1 repo3.7k2018

Precise Facial Landmark Detection by Dynamic Semantic Aggregation Transformer

85% match2024

Disjoint Pose and Shape for 3D Face Reconstruction

84% match1 repo32023

Cite this paper

@article{feng2018joint,
  title  = {Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network},
  author = {Yao Feng and Fan Wu and Xiaohu Shao and Yanfeng Wang and Xi Zhou},
  year   = {2018},
  eprint = {1803.07835},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1803.07835}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1803.07835.svg)](https://codeofpaper.com/paper/1803.07835)

Discussion