Towards 3D Face Reconstruction in Perspective Projection: Estimating 6DoF Face Pose from Monocular Image

TL;DR

This paper introduces PerspNet, a deep neural network that reconstructs 3D face shape and estimates 6DoF pose from monocular images under perspective projection, addressing limitations of orthogonal projection methods in close-range scenarios.

Contribution

The paper proposes PerspNet for accurate 3D face reconstruction and pose estimation under perspective projection, along with a large ARKitFace dataset for training and evaluation.

Findings

Outperforms state-of-the-art methods significantly

Provides accurate 6DoF pose estimation from monocular images

Enables robust 3D face reconstruction in close-range scenarios

Abstract

In 3D face reconstruction, orthogonal projection has been widely employed to substitute perspective projection to simplify the fitting process. This approximation performs well when the distance between camera and face is far enough. However, in some scenarios that the face is very close to camera or moving along the camera axis, the methods suffer from the inaccurate reconstruction and unstable temporal fitting due to the distortion under the perspective projection. In this paper, we aim to address the problem of single-image 3D face reconstruction under perspective projection. Specifically, a deep neural network, Perspective Network (PerspNet), is proposed to simultaneously reconstruct 3D face shape in canonical space and learn the correspondence between 2D pixels and 3D points, by which the 6DoF (6 Degrees of Freedom) face pose can be estimated to represent perspective projection. Besides, we contribute a large ARKitFace dataset to enable the training and evaluation of 3D face reconstruction solutions under the scenarios of perspective projection, which has 902,724 2D facial images with ground-truth 3D face mesh and annotated 6DoF pose parameters. Experimental results show that our approach outperforms current state-of-the-art methods by a significant margin. The code and data are available at https://github.com/cbsropenproject/6dof_face.