StyleUV: Diverse and High-fidelity UV Map Generative Model
This work addresses the problem of generating high-quality and diverse 3D human face textures for researchers and applications relying on 3D Morphable Models, offering an incremental improvement by removing the need for expensive UV map datasets.
The paper introduces StyleUV, a novel generative model for creating diverse and realistic synthetic UV maps for 3D human faces. It tackles the problem of limited high-quality UV map data by training solely on in-the-wild 2D images, leveraging GANs and a differentiable renderer, and achieves higher fidelity and diversity compared to existing methods.
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.