XingangPan/ShadeGAN
Code for ShadeGAN (NeurIPS2021)
This project helps 3D artists, game developers, or researchers generate realistic, 3D-aware images of objects or faces from various viewpoints and lighting conditions. You provide a dataset of 2D images (like human faces or cats), and it produces new, high-quality images with accurate 3D shapes that you can rotate and relight. This is ideal for anyone needing to create diverse 3D content from existing 2D image collections.
146 stars. No commits in the last 6 months.
Use this if you need to create diverse 3D models and images with realistic lighting and viewpoints from a collection of 2D photos.
Not ideal if you need to generate images of arbitrary objects or scenes not represented in existing datasets, or if you require real-time 3D rendering for interactive applications.
Stars
146
Forks
22
Language
Python
License
MIT
Category
Last pushed
Oct 17, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/XingangPan/ShadeGAN"
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".