k8xu/amodal

Official code for "Amodal Completion via Progressive Mixed Context Diffusion" [CVPR 2024 Highlight]

25
/ 100
Experimental

This project helps computer vision researchers and developers restore the complete appearance of objects in images, even when parts are hidden or cut off. You input an image with an occluded object, and it outputs the original image with the missing parts of the object filled in, as if the obstruction was removed. It's designed for those working with image analysis, reconstruction, or scene understanding.

No commits in the last 6 months.

Use this if you need to accurately reconstruct the full form of objects in images that are partially hidden by other objects or cut off by the image boundary, without needing extensive custom model training.

Not ideal if you're looking for a simple, out-of-the-box application for everyday photo editing, as it requires some technical setup.

computer-vision image-reconstruction object-recognition scene-understanding image-inpainting
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

55

Forks

4

Language

Jupyter Notebook

License

Last pushed

Jul 24, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/k8xu/amodal"

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