CNN-based Real-time Dense Face Reconstruction with Inverse-rendered Photo-realistic Face Images

TL;DR

This paper introduces a novel data generation method and a coarse-to-fine CNN framework for real-time, detailed 3D face reconstruction from images and videos, achieving high quality with less computation.

Contribution

It presents a new inverse-rendering based data synthesis approach and a multi-network framework for efficient, detailed face reconstruction that outperforms existing methods.

Findings

Produces high-quality 3D face reconstructions in real-time

Robust to pose, expression, and lighting variations

Requires less computation than state-of-the-art methods

Abstract

With the powerfulness of convolution neural networks (CNN), CNN based face reconstruction has recently shown promising performance in reconstructing detailed face shape from 2D face images. The success of CNN-based methods relies on a large number of labeled data. The state-of-the-art synthesizes such data using a coarse morphable face model, which however has difficulty to generate detailed photo-realistic images of faces (with wrinkles). This paper presents a novel face data generation method. Specifically, we render a large number of photo-realistic face images with different attributes based on inverse rendering. Furthermore, we construct a fine-detailed face image dataset by transferring different scales of details from one image to another. We also construct a large number of video-type adjacent frame pairs by simulating the distribution of real video data. With these nicely constructed datasets, we propose a coarse-to-fine learning framework consisting of three convolutional networks. The networks are trained for real-time detailed 3D face reconstruction from monocular video as well as from a single image. Extensive experimental results demonstrate that our framework can produce high-quality reconstruction but with much less computation time compared to the state-of-the-art. Moreover, our method is robust to pose, expression and lighting due to the diversity of data.