shepnerd/inpainting_gmcnn
Image Inpainting via Generative Multi-column Convolutional Neural Networks, NeurIPS2018
Multi-column convolutional architecture with parallel pathways of varying receptive fields to capture both coarse structure and fine details. Employs a two-stage training pipeline: confidence-driven reconstruction pretraining followed by adversarial and ID-MRF loss finetuning. Supports both TensorFlow 1.4+ and PyTorch implementations with pretrained models for Places2, CelebA-HQ, and Paris StreetView datasets, handling rectangular and freeform stroke masks.
436 stars. No commits in the last 6 months.
Stars
436
Forks
97
Language
Python
License
MIT
Category
Last pushed
Mar 01, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/shepnerd/inpainting_gmcnn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
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...
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".
kkakkkka/HunyuanPortraitLCM
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...