3D-GANTex: 3D Face Reconstruction with StyleGAN3-based Multi-View Images and 3DDFA based Mesh Generation

Rohit Das, Tzung-Han Lin, Ko-Chih Wang
10/21/2024
cs.CV

No official code found. Best implementation: rohit7044/3D-GANTex (59 stars, MIT, last commit 2025-02-22).

Abstract

Geometry and texture estimation from a single face image is an ill-posed problem since there is very little information to work with. The problem further escalates when the face is rotated at a different angle. This paper tries to tackle this problem by introducing a novel method for texture estimation from a single image by first using StyleGAN and 3D Morphable Models. The method begins by generating multi-view faces using the latent space of GAN. Then 3DDFA trained on 3DMM estimates a 3D face mesh as well as a high-resolution texture map that is consistent with the estimated face shape. The result shows that the generated mesh is of high quality with near to accurate texture representation.

View on arXivView PDF

Code Implementations(1)

rohit7044/3D-GANTexCommunity100%
MIT

3DGANTex: 3D Face Reconstruction with StyleGAN3-based Texture Synthesis from Multi-View Images

595C, C++May 18, 20231 years agoMIT
3d-face-reconstruction3d-model3ddfaganlatent-space+2 more

Similar Papers

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

84% match2024

Text-Driven Diverse Facial Texture Generation via Progressive Latent-Space Refinement

83% match2024

FreeUV: Ground-Truth-Free Realistic Facial UV Texture Recovery via Cross-Assembly Inference Strategy

82% match1 repo232025

Towards High-Fidelity 3D Face Reconstruction from In-the-Wild Images Using Graph Convolutional Networks

82% match1 repo4022020

SMPLitex: A Generative Model and Dataset for 3D Human Texture Estimation from Single Image

81% match2023

SMPL-GPTexture: Dual-View 3D Human Texture Estimation using Text-to-Image Generation Models

81% match2025

Cite this paper

@article{das2024dgantex,
  title  = {3D-GANTex: 3D Face Reconstruction with StyleGAN3-based Multi-View Images and 3DDFA based Mesh Generation},
  author = {Rohit Das and Tzung-Han Lin and Ko-Chih Wang},
  year   = {2024},
  eprint = {2410.16009},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.16009v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.16009.svg)](https://codeofpaper.com/paper/2410.16009)

Discussion