StyleUV: Diverse and High-fidelity UV Map Generative Model

TL;DR

This paper introduces StyleUV, a generative model that creates diverse, high-fidelity UV maps for 3D face reconstruction without needing high-quality UV map training data, leveraging GANs and differentiable rendering.

Contribution

The work presents a novel UV map generative model trained solely on in-the-wild images, improving texture diversity and quality without high-quality UV map datasets.

Findings

Produces more diverse UV maps than existing methods.

Generates higher fidelity textures in 3D face reconstruction.

Operates without requiring high-quality UV map training data.

Abstract

Reconstructing 3D human faces in the wild with the 3D Morphable Model (3DMM) has become popular in recent years. While most prior work focuses on estimating more robust and accurate geometry, relatively little attention has been paid to improving the quality of the texture model. Meanwhile, with the advent of Generative Adversarial Networks (GANs), there has been great progress in reconstructing realistic 2D images. Recent work demonstrates that GANs trained with abundant high-quality UV maps can produce high-fidelity textures superior to those produced by existing methods. However, acquiring such high-quality UV maps is difficult because they are expensive to acquire, requiring laborious processes to refine. In this work, we present a novel UV map generative model that learns to generate diverse and realistic synthetic UV maps without requiring high-quality UV maps for training. Our proposed framework can be trained solely with in-the-wild images (i.e., UV maps are not required) by leveraging a combination of GANs and a differentiable renderer. Both quantitative and qualitative evaluations demonstrate that our proposed texture model produces more diverse and higher fidelity textures compared to existing methods.