Tandon-A/CycleGAN_ssim
Comparing different similarity functions for reconstruction of image on CycleGAN. (https://tandon-a.github.io/CycleGAN_ssim/) Training cycleGAN with different loss functions to improve visual quality of produced images
This project helps image processors and digital artists transform images between distinct visual styles, like turning a photograph into a painting, or vice-versa. You provide two collections of images, each representing a different style or domain. The project then generates new images that have the style of one collection while retaining the content of the other. Anyone involved in creative visual content generation or research into image-to-image translation would use this.
No commits in the last 6 months.
Use this if you need to translate images from one visual domain to another, such as converting sketches to photorealistic images or changing seasonal scenes, and want to experiment with different quality settings.
Not ideal if you need to perform simple image edits like cropping, resizing, or color correction, or if you're looking for a user-friendly graphical interface.
Stars
83
Forks
8
Language
Python
License
MIT
Category
Last pushed
Feb 16, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Tandon-A/CycleGAN_ssim"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yunjey/domain-transfer-network
TensorFlow Implementation of Unsupervised Cross-Domain Image Generation
taesungp/contrastive-unpaired-translation
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV...
PaddlePaddle/PaddleGAN
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion...
tohinz/ConSinGAN
PyTorch implementation of "Improved Techniques for Training Single-Image GANs" (WACV-21)
sagiebenaim/DistanceGAN
Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017