Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network
This provides a fast, accurate solution for 3D facial analysis applications like animation and biometrics, though it is an incremental improvement over existing methods.
The paper tackles 3D face reconstruction and dense alignment from single 2D images by proposing a UV position map representation and training a CNN to regress it, achieving state-of-the-art results with processing times of 9.8ms per image.
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.