Model Description

• SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation
• Zheng, Xin-Yang and Liu, Yang and Wang, Peng-Shuai and Tong, Xin, 2022

The proposed deeplearning model for 3D shape generation called signed distance field (SDF) - SDF-StyleGAN, whicH is based on StyleGAN2. The goal of this approach is to minimize the visual and geometric differences between the generated shapes and a collection of existing shapes.

Documents

• GitHub Repo
• Paper - SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation

Datasets

ShapeNet is a comprehensive 3D shape dataset created for research in computer graphics, computer vision, robotics and related diciplines.

• Offical Dataset of ShapeNet
• author's data preparation script
• author's training data

How to use

Training snippets are published under the official GitHub repository above.

BibTeX Entry and Citation Info

@inproceedings{zheng2022sdfstylegan,
 title = {SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation},
 author = {Zheng, Xin-Yang and Liu, Yang and Wang, Peng-Shuai and Tong, Xin},
 booktitle = {Comput. Graph. Forum (SGP)},
 year = {2022},
}