On Learning 3D Face Morphable Model from In-the-wild Images

08/28/2018
by   Luan Tran, et al.
2

As a classic statistical model of 3D facial shape and albedo, 3D Morphable Model (3DMM) is widely used in facial analysis, e.g., model fitting, image synthesis. Conventional 3DMM is learned from a set of 3D face scans with associated well-controlled 2D face images, and represented by two sets of PCA basis functions. Due to the type and amount of training data, as well as, the linear bases, the representation power of 3DMM can be limited. To address these problems, this paper proposes an innovative framework to learn a nonlinear 3DMM model from a large set of in-the-wild face images, without collecting 3D face scans. Specifically, given a face image as input, a network encoder estimates the projection, lighting, shape and albedo parameters. Two decoders serve as the nonlinear 3DMM to map from the shape and albedo parameters to the 3D shape and albedo, respectively. With the projection parameter, lighting, 3D shape, and albedo, a novel analytically-differentiable rendering layer is designed to reconstruct the original input face. The entire network is end-to-end trainable with only weak supervision. We demonstrate the superior representation power of our nonlinear 3DMM over its linear counterpart, and its contribution to face alignment, 3D reconstruction, and face editing.

READ FULL TEXT

page 5

page 7

page 8

page 9

page 10

page 11

page 12

page 13

research
04/11/2018

Nonlinear 3D Face Morphable Model

As a classic statistical model of 3D facial shape and texture, 3D Morpha...
research
05/31/2021

Learning Free-Form Deformation for 3D Face Reconstruction from In-The-Wild Images

The 3D Morphable Model (3DMM), which is a Principal Component Analysis (...
research
04/09/2019

Towards High-fidelity Nonlinear 3D Face Morphable Model

Embedding 3D morphable basis functions into deep neural networks opens g...
research
08/03/2020

GmFace: A Mathematical Model for Face Image Representation Using Multi-Gaussian

Establishing mathematical models is a ubiquitous and effective method to...
research
02/18/2019

Decomposing multispectral face images into diffuse and specular shading and biophysical parameters

We propose a novel biophysical and dichromatic reflectance model that ef...
research
04/06/2020

A Morphable Face Albedo Model

In this paper, we bring together two divergent strands of research: phot...
research
08/22/2017

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

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

Please sign up or login with your details

Forgot password? Click here to reset