JIA-Lab-research/outpainting_srn
Wide-Context Semantic Image Extrapolation, CVPR2019
This tool helps you expand the boundaries of an existing image, intelligently filling in missing content that makes sense with the original picture. You provide a cropped image of a face, body, or scene, and it generates a wider version, adding realistic surroundings or completing subjects. It's designed for creative professionals like graphic designers, photographers, or marketers who need to adjust image aspect ratios or fill in missing visual information.
135 stars. No commits in the last 6 months.
Use this if you need to semantically expand images beyond their original boundaries, like uncropping a portrait or extending a landscape.
Not ideal if you need perfectly stable performance across a wide variety of untrained, large-scale datasets or if you're looking for an inpainting tool to fill in holes within an image.
Stars
135
Forks
32
Language
Python
License
MIT
Category
Last pushed
Sep 03, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/JIA-Lab-research/outpainting_srn"
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