xcyan/neurips18_hierchical_image_manipulation

Pytorch Implementation of NeurIPS'18 paper on Generative Image Manipulation with Hierarchical Semantic Structures

43
/ 100
Emerging

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.

Computer Vision Research Generative Models Image Synthesis Semantic Segmentation Scene Generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

69

Forks

21

Language

Python

License

MIT

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.