sofgan icon indicating copy to clipboard operation
sofgan copied to clipboard

[TOG 2022] SofGAN: A Portrait Image Generator with Dynamic Styling

Results 21 sofgan issues
Sort by recently updated
recently updated
newest added

What are the attributes of segmap for every class? Thank you!

When drawing admittedly unrealistic eye sizes sofgan will repeat an iris and corners inside of the eye instead of making a larger iris to fill the eye shape. This is...

Hi, I am trying to use this model to edit real-captured photos but I think the exsisting renderer.ipynb file only using the random style. In the paper, there are visualization...

How do you do it here https://www.youtube.com/watch?v=xig8ZA3DVZ8 at 5:12?

大佬,运行Painter/run_UI.py后能画图,但是右边出不来图片。点击Render或者change style后,提示我需要指定load checkpoint。 而run_UI.py中,load checkpoint时,需要load一个model,在modules/sofgan.pt. 然而在工程下没有找到这个pt的下载路径。 Rendering中下载的checkpoint文件中,也没有这个pt文件。 求问怎么操作。。。

Hi, and thank you for your amazing work! In SIW-StyleGAN architecture, the classwiseStyle parameter is always set to False, but what is it for? In which cases should it be...

as described:how to generate mutiview segmap for own image ,just like trump

想请教一下segNet-20Class.pth这个模型是怎么训练出来的呢?还有condition img那个segmaps的文件夹实际是什么意义呢?

@apchenstu ,作者您好,向您请教一个问题,我看到文章中有提到对于真实图片进行纹理样式替换的做法,我按照您的步骤, 当我使用重建得到W+ latent [18,512],和random得到的w+ [2,18,512]中的[1,18,512],拼接成新的W+[2,18,512]后进行头发区域风格编辑,得到的图刘海部分会有红边,如下图所示 ![image](https://user-images.githubusercontent.com/59382173/141068791-787f63b3-c8bd-4b41-8f40-251f077edfa7.png) 但是当我使用重建得到的W latent [512], 和random得到的styles [2,512]中的[1,512],拼接成新的style后转为W+ [2,18,512]就不会出现上图的问题,但是W空间重建后的图又和原图差异特别大,如下图所示,很难看出这个和上面的是一个人 ![image](https://user-images.githubusercontent.com/59382173/141069424-c85b2e57-b357-470a-afa6-7bfe785105b6.png) 。 请问作者,我对真实图片进行区域纹理样式改变的做法哪个环节出了问题,我应该怎么去做,期待您的回复,辛苦了!

Hi, Thanks for your solid work with released codes. I wonder if there is any scripts for reproduing the texture styling results of fig 12 in your paper, i.e. given...