VGG-Tex: A Vivid Geometry-Guided Facial Texture Estimation Model for High Fidelity Monocular 3D Face Reconstruction

TL;DR

VGG-Tex is a novel model that enhances 3D face reconstruction from monocular images by integrating geometry priors and texture refinement modules, achieving high-fidelity facial textures.

Contribution

It introduces a comprehensive framework combining geometry-guided texture estimation and refinement modules for improved 3D face reconstruction.

Findings

Significantly outperforms existing methods in texture reconstruction quality.

Effectively balances geometry and texture fidelity in 3D face models.

Demonstrates robustness across diverse facial images.

Abstract

3D face reconstruction from monocular images has promoted the development of various applications such as augmented reality. Though existing methods have made remarkable progress, most of them emphasize geometric reconstruction, while overlooking the importance of texture prediction. To address this issue, we propose VGG-Tex, a novel Vivid Geometry-Guided Facial Texture Estimation model designed for High Fidelity Monocular 3D Face Reconstruction. The core of this approach is leveraging 3D parametric priors to enhance the outcomes of 2D UV texture estimation. Specifically, VGG-Tex includes a Facial Attributes Encoding Module, a Geometry-Guided Texture Generator, and a Visibility-Enhanced Texture Completion Module. These components are responsible for extracting parametric priors, generating initial textures, and refining texture details, respectively. Based on the geometry-texture complementarity principle, VGG-Tex also introduces a Texture-guided Geometry Refinement Module to further balance the overall fidelity of the reconstructed 3D faces, along with corresponding losses. Comprehensive experiments demonstrate that our method significantly improves texture reconstruction performance compared to existing state-of-the-art methods.