Wuziyi616/SlotDiffusion

Code release for NeurIPS 2023 paper SlotDiffusion: Object-centric Learning with Diffusion Models

38
/ 100
Emerging

This project helps researchers and developers working with computer vision automatically identify and isolate distinct objects within images and video without needing extensive manual labeling. It takes raw images or video frames and outputs segmented objects, which are then used for tasks like image editing or video prediction. This is for AI/ML researchers, computer vision engineers, and data scientists developing new object recognition and scene understanding applications.

No commits in the last 6 months.

Use this if you need to perform unsupervised object segmentation, image editing, or compositional generation from visual data, especially for research and development of new computer vision models.

Not ideal if you are looking for an off-the-shelf application for immediate production use or do not have access to a Slurm GPU cluster.

computer-vision-research unsupervised-learning image-segmentation video-analysis generative-models
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

94

Forks

11

Language

Python

License

MIT

Last pushed

Jan 16, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Wuziyi616/SlotDiffusion"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.