Enhanced 3DMM Attribute Control via Synthetic Dataset Creation Pipeline
This work is significant for computer vision and graphics researchers working on 3D facial attribute manipulation, as it tackles the fundamental data scarcity problem and offers a more precise control method.
This paper addresses the lack of paired 3D facial data for attribute manipulation by proposing a novel pipeline that leverages GANs to generate such data. This pipeline enables an enhanced non-linear 3D conditional attribute controller, which improves the precision and diversity of 3D attribute control compared to existing methods.
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.