hkchengrex/Tracking-Anything-with-DEVA

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation

48
/ 100
Emerging

This project helps video editors, content creators, or analysts automatically track and segment any object across video frames. You provide a video and a text description (e.g., "guinea pigs," "capybara," "person with hat"), and the tool outputs a video with the specified objects precisely outlined and followed throughout the footage. It's ideal for anyone needing to isolate or analyze specific elements in video content without manual, frame-by-frame effort.

1,487 stars. No commits in the last 6 months.

Use this if you need to accurately highlight and follow specific objects or categories of objects in a video, even if they appear, disappear, or change position.

Not ideal if your primary goal is to segment objects from static images, or if you need to precisely track objects in very short clips where dedicated, end-to-end video segmentation models trained specifically on that type of data might perform better.

video-editing content-analysis motion-tracking visual-effects object-detection
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

1,487

Forks

139

Language

Python

License

Last pushed

Apr 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/hkchengrex/Tracking-Anything-with-DEVA"

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