Enhanced 3DMM Attribute Control via Synthetic Dataset Creation Pipeline

TL;DR

This paper introduces a pipeline for generating paired 3D face datasets using GANs and proposes an improved 3D attribute controller, enabling more precise and diverse manipulation of 3D facial attributes.

Contribution

The paper presents a novel dataset creation pipeline for 3D faces and an enhanced non-linear 3D attribute controller, addressing the lack of paired training data and improving attribute manipulation.

Findings

Generated paired 3D face datasets effectively.

Enhanced attribute control accuracy and diversity.

Validated through quantitative and qualitative evaluations.

Abstract

While facial attribute manipulation of 2D images via Generative Adversarial Networks (GANs) has become common in computer vision and graphics due to its many practical uses, research on 3D attribute manipulation is relatively undeveloped. Existing 3D attribute manipulation methods are limited because the same semantic changes are applied to every 3D face. The key challenge for developing better 3D attribute control methods is the lack of paired training data in which one attribute is changed while other attributes are held fixed -- e.g., a pair of 3D faces where one is male and the other is female but all other attributes, such as race and expression, are the same. To overcome this challenge, we design a novel pipeline for generating paired 3D faces by harnessing the power of GANs. On top of this pipeline, we then propose an enhanced non-linear 3D conditional attribute controller that increases the precision and diversity of 3D attribute control compared to existing methods. We demonstrate the validity of our dataset creation pipeline and the superior performance of our conditional attribute controller via quantitative and qualitative evaluations.