Nonlinear 3D Face Morphable Model

TL;DR

This paper introduces a nonlinear 3D face morphable model learned from large, unconstrained face images, enhancing face analysis tasks like alignment and reconstruction without needing 3D scans.

Contribution

It proposes a novel end-to-end trainable nonlinear 3DMM framework that surpasses linear models in representation power using only weak supervision.

Findings

Outperforms linear 3DMM in face reconstruction accuracy

Enables 3D face modeling without 3D scan data

Improves face alignment and reconstruction results

Abstract

As a classic statistical model of 3D facial shape and texture, 3D Morphable Model (3DMM) is widely used in facial analysis, e.g., model fitting, image synthesis. Conventional 3DMM is learned from a set of well-controlled 2D face images with associated 3D face scans, 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 unconstrained face images, without collecting 3D face scans. Specifically, given a face image as input, a network encoder estimates the projection, shape and texture parameters. Two decoders serve as the nonlinear 3DMM to map from the shape and texture parameters to the 3D shape and texture, respectively. With the projection parameter, 3D shape, and texture, 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 and 3D reconstruction.