matlab-deep-learning/pix2pix
Image to Image Translation Using Generative Adversarial Networks
This project helps graphic designers, architects, or urban planners transform simple input images, like line drawings or semantic segmentation maps, into realistic-looking visual outputs. You provide pairs of 'before' and 'after' images, and it learns to generate new 'after' images from new 'before' inputs. This is ideal for anyone needing to quickly visualize concepts or designs with greater realism.
No commits in the last 6 months.
Use this if you need to automatically convert conceptual sketches or simplified visual representations into photorealistic images.
Not ideal if you don't have many pairs of 'before' and 'after' images to train the system, or if your images are not simple translations (e.g., generating entirely new content from text).
Stars
35
Forks
12
Language
MATLAB
License
—
Category
Last pushed
May 12, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/matlab-deep-learning/pix2pix"
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