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

Yao Feng, Fan Wu, Xiaohu Shao, Yanfeng Wang, Xi Zhou; The European Conference on Computer Vision (ECCV), 2018, pp. 534-551

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. Code is available at https://github.com/YadiraF/PRNet.

Related Material


[pdf]
[bibtex]
@InProceedings{Feng_2018_ECCV,
author = {Feng, Yao and Wu, Fan and Shao, Xiaohu and Wang, Yanfeng and Zhou, Xi},
title = {Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network},
booktitle = {The European Conference on Computer Vision (ECCV)},
month = {September},
year = {2018}
}