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

Yao Feng, Fan Wu, Xiaohu Shao, Yanfeng Wang, Xi Zhou
2018 arXiv   pre-print
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
more » ... l, 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.
arXiv:1803.07835v1 fatcat:sybi46n4wzamvgj72j3u23gpbe