hkchengrex/XMem

[ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

46
/ 100
Emerging

This tool helps video editors, content creators, and VFX artists automatically separate specific objects from their backgrounds in long video sequences. You provide a video and mark the object you care about in the first frame, and it outputs the video with that object precisely outlined in every subsequent frame, even through occlusions or complex movements. It's designed for anyone needing to isolate elements for visual effects, compositing, or detailed analysis.

1,962 stars. No commits in the last 6 months.

Use this if you need to accurately track and segment a specific object across an entire video, especially very long ones, with minimal manual effort.

Not ideal if you need to segment multiple objects at once without prior selection or if precise, real-time object detection for live streams is your primary goal.

video-editing visual-effects content-creation object-tracking video-segmentation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

1,962

Forks

207

Language

Python

License

MIT

Last pushed

Nov 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/hkchengrex/XMem"

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