xcyan/neurips18_hierchical_image_manipulation
Pytorch Implementation of NeurIPS'18 paper on Generative Image Manipulation with Hierarchical Semantic Structures
This project helps researchers and academics in computer vision generate realistic images from semantic layouts or object bounding boxes. You input structured information, like bounding boxes describing objects and their locations, or detailed semantic segmentation masks, and it outputs a high-fidelity image that matches your specified scene. It's designed for those exploring generative models and image synthesis techniques.
No commits in the last 6 months.
Use this if you need to research or experiment with generating photorealistic images from high-level scene descriptions or modifying existing scene elements like buildings or roads.
Not ideal if you're looking for an off-the-shelf application for general image editing or content creation without a deep understanding of machine learning models.
Stars
69
Forks
21
Language
Python
License
MIT
Category
Last pushed
Sep 19, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/xcyan/neurips18_hierchical_image_manipulation"
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