Saved in:
Bibliographic Details
Main Authors: Das, Rohit, Lin, Tzung-Han, Wang, Ko-Chih
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.16009
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914982883491840
author Das, Rohit
Lin, Tzung-Han
Wang, Ko-Chih
author_facet Das, Rohit
Lin, Tzung-Han
Wang, Ko-Chih
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16009
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle 3D-GANTex: 3D Face Reconstruction with StyleGAN3-based Multi-View Images and 3DDFA based Mesh Generation
Das, Rohit
Lin, Tzung-Han
Wang, Ko-Chih
Computer Vision and Pattern Recognition
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.
title 3D-GANTex: 3D Face Reconstruction with StyleGAN3-based Multi-View Images and 3DDFA based Mesh Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.16009