comzzw/Generative-Image-Inpainting
[AAAI2023, Oral] Official Implementation of Generative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive Learning
This project helps remove unwanted elements or repair damaged areas in images by intelligently filling in missing regions. It takes an image with a 'hole' or masked area and generates new, plausible content to seamlessly blend with the existing image. Professionals in visual media, such as graphic designers, photographers, or marketers, would find this useful for image retouching and restoration.
No commits in the last 6 months.
Use this if you need to realistically repair or remove specific sections from images, creating content that is visually consistent with the surrounding areas.
Not ideal if you're looking for a simple, automated 'one-click' fix for minor imperfections without needing high-fidelity content generation.
Stars
23
Forks
2
Language
Python
License
—
Category
Last pushed
Oct 17, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/comzzw/Generative-Image-Inpainting"
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".