https://github.com/yifan123/selfie-cartoonization-gan

https://github.com/yifan123/selfie-cartoonization-gan

Last synced: 6 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/yifan123/selfie-cartoonization-gan
• Owner: yifan123
• Created: 2019-06-12T08:18:22.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2019-08-25T01:45:55.000Z (about 5 years ago)
• Last Synced: 2024-02-29T13:58:31.225Z (9 months ago)
• Size: 9.6 MB
• Stars: 15
• Watchers: 3
• Forks: 1
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# selfie-Cartoonization-GAN

This is our project which can convert a selfie to a hand-painted cartoon image by GAN. This work is motivated by CartoonGAN.  However, CartoonGAN cannot avoid the influence of background if background doesn’t belong to style. We add a segmentation network(Unet) to solve the problem. More information can be seen in the [slide]().

We build two new datasets 

- a hand-painted cartoon image [dataset]();

  ![dataset](images/dataset.jpg)

  

  

  

- an identification photo dataset.

The following are sources of training image

- Baidu image

- Google image

- Taobao comments

The following are dataset information.

| **Selfie**           | **Numbers** |

| -------------------- | ----------- |

| celebA               | 350         |

| identification photo | 340         |

| **Style**    | **Numers** |

| ------------ | ---------- |

| Hand-painted | 311        |

The following are our results.

 ![photo](images/photo.jpg)

![celebA](images/celebA.jpg)

You may see that the background of the 1st row is red. To make it more interesting, I changed the background of the 1st row to red color by photoshop. However, others are indeed directly generated by our model.