jgkwak95/AU-GAN
Official Tensorflow implementation for "Adverse Weather Image Translation with Asymmetric and Uncertainty aware GAN", BMVC2021
This project helps convert adverse weather images into clear, daytime images, useful for training autonomous vehicles or enhancing surveillance. It takes images captured in conditions like night or rainy night and transforms them into their daytime equivalents. This would be used by researchers and engineers working on computer vision for autonomous driving or smart city applications.
No commits in the last 6 months.
Use this if you need to transform images captured in challenging lighting or weather conditions (like night or rainy night) into clear daytime images for analysis or further processing.
Not ideal if you need to process video streams in real-time or if your primary goal is general image style transfer unrelated to weather conditions.
Stars
79
Forks
10
Language
Python
License
—
Category
Last pushed
Jul 23, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/jgkwak95/AU-GAN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pathak22/context-encoder
[CVPR 2016] Unsupervised Feature Learning by Image Inpainting using GANs
knazeri/edge-connect
EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019...
shepnerd/inpainting_gmcnn
Image Inpainting via Generative Multi-column Convolutional Neural Networks, NeurIPS2018
youyuge34/Anime-InPainting
An application tool of edge-connect, which can do anime inpainting and drawing. 动漫人物图片自动修复，去马赛克，填补，去瑕疵
otenim/GLCIC-PyTorch
A High-Quality PyTorch Implementation of "Globally and Locally Consistent Image Completion".