0zgur0/Sequential-Scene-GAN
[AAAI 2019] A Layer-Based Sequential Framework for Scene Generation with GANs
This project helps researchers and artists create complex, realistic images by generating them in layers. You provide a general idea or style, and it produces detailed scene images by building backgrounds and then adding foreground elements. It's designed for anyone working in computer vision research, synthetic data generation, or creative artificial intelligence who needs to generate diverse and structured visual content.
No commits in the last 6 months.
Use this if you need to generate synthetic images with distinct background and foreground elements for research, dataset expansion, or creative applications.
Not ideal if you need to generate simple, single-object images or require precise, pixel-level control over every generated element without AI assistance.
Stars
40
Forks
10
Language
Python
License
—
Category
Last pushed
May 25, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/0zgur0/Sequential-Scene-GAN"
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