search

kmes055 / AutoDrawer

Capstone project in dept. of CS. Application for designers, artists using TextureGAN, DisgoGAN
0 stars 1 forks source link

Technical Stack summary #24

Open kmes055 opened 5 years ago

kmes055 commented 5 years ago

Fix all technical stacks & requirements

hacking-racoon commented 5 years ago

One of most popular Network Librarys are Retrofit 2, Volley.

But I found a great library for image_transfer.

this library is very easy to use.

https://github.com/gungoronline/Photto

(Android Studio)

hacking-racoon commented 5 years ago

HTML ( 생활코딩 https://opentutorials.org/course/3084 ) CSS ( 생활코딩 https://opentutorials.org/course/2418 ) JS ( 노마드코더 https://academy.nomadcoders.co )

kmes055 commented 5 years ago

Dataset citations(TODO): Shoes dataset: training images from UT Zappos50K dataset. Hangbags dataset: Amazon Handbag images from iGAN project. Deep Fashion Dataset: clothes images from Deep Fashion Dataset.

Paper citations(TODO): Pix2pix HED(maybe?) CycleGAN(maybe one in pix2pix repo)

kmes055 commented 5 years ago

Doing preprocessing for image->edge with pix2pix or HED. Both networks are in training, will check later. AI part is quite complex and various, We'll use another repo for AI Here.

kmes055 commented 5 years ago

Add: Please write references for papers below

Isola et al, "Image-to-Image Translation with Conditional Adversarial Networks", in Conference on Computer Vision and Pattern Recognition(CVPR), 2017 JY Zhu et al. "Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks", in IEEE International Conference on Computer Vision (ICCV), 2017 S Xie et al. "Holistically-Nested Edge Detection", in IEEE International Conference on Computer Vision (ICCV), 2015