thiagoambiel/NeuralAtlases

📺 NeuralAtlases - A Pytorch implementation of the paper "Layered Neural Atlases for Consistent Video Editing" (https://arxiv.org/abs/2109.11418v1)

35
/ 100
Emerging

This helps video editors and visual effects artists apply changes to specific elements within a video consistently across all frames. You provide a video and, optionally, rough 'scribble' guidance on what parts belong to different layers (like foreground or background). The output is an 'atlas' representation of your video that allows you to make edits to objects or backgrounds once, and have those changes automatically reflected throughout the entire video.

No commits in the last 6 months.

Use this if you need to edit specific foreground or background elements in a video and want changes to remain perfectly consistent and seamless from frame to frame.

Not ideal if you're looking for simple, whole-video color correction or basic cuts; this tool is for more advanced, object-specific manipulation.

video-editing visual-effects motion-graphics post-production creative-media
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

34

Forks

5

Language

Python

License

MIT

Last pushed

Feb 17, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/thiagoambiel/NeuralAtlases"

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