Learning 3D Face Reconstruction with a Pose Guidance Network

TL;DR

This paper introduces a self-supervised method for monocular 3D face reconstruction using a pose guidance network that leverages 3D landmarks and multi-frame geometry to improve accuracy and robustness.

Contribution

It proposes a novel pose guidance network and self-supervised scheme that combine parametric and data-driven learning for 3D face reconstruction from monocular images.

Findings

Outperforms state-of-the-art on AFLW2000-3D, Florence, and FaceWarehouse datasets.

Effectively utilizes unlabeled in-the-wild images and multi-frame data.

Addresses pose estimation bottleneck in 3D face learning.

Abstract

We present a self-supervised learning approach to learning monocular 3D face reconstruction with a pose guidance network (PGN). First, we unveil the bottleneck of pose estimation in prior parametric 3D face learning methods, and propose to utilize 3D face landmarks for estimating pose parameters. With our specially designed PGN, our model can learn from both faces with fully labeled 3D landmarks and unlimited unlabeled in-the-wild face images. Our network is further augmented with a self-supervised learning scheme, which exploits face geometry information embedded in multiple frames of the same person, to alleviate the ill-posed nature of regressing 3D face geometry from a single image. These three insights yield a single approach that combines the complementary strengths of parametric model learning and data-driven learning techniques. We conduct a rigorous evaluation on the challenging AFLW2000-3D, Florence and FaceWarehouse datasets, and show that our method outperforms the state-of-the-art for all metrics.