Single-Image 3D Face Reconstruction under Perspective Projection

by   Yueying Kao, et al.

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.


page 13

page 14

page 19

page 20

page 21


Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction

As it is hard to calibrate single-view RGB images in the wild, existing ...

Towards Metrical Reconstruction of Human Faces

Face reconstruction and tracking is a building block of numerous applica...

What does 2D geometric information really tell us about 3D face shape?

A face image contains geometric cues in the form of configurational info...

MaskBot: Real-time Robotic Projection Mapping with Head Motion Tracking

The projection mapping systems on the human face is limited by the laten...

Learning Perspective Undistortion of Portraits

Near-range portrait photographs often contain perspective distortion art...

PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layers

Local processing is an essential feature of CNNs and other neural networ...

DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs

Close-up facial images captured at close distances often suffer from per...

Please sign up or login with your details

Forgot password? Click here to reset