msu-video-group/memfof

[ICCV'2025 Highlight] MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation

36
/ 100
Emerging

This tool helps computer vision engineers and researchers accurately estimate motion between frames in Full HD video sequences, even with limited GPU memory. You provide a video, and it outputs detailed optical flow maps showing how objects or pixels move across consecutive frames. This is ideal for anyone working on video analysis tasks like action recognition, object tracking, or video stabilization.

Use this if you need to analyze movement in high-resolution videos (Full HD or similar) and want to achieve high accuracy without demanding excessive GPU memory.

Not ideal if your primary goal is real-time processing on very low-power devices, or if you only work with low-resolution video where memory efficiency isn't a major concern.

video-analysis motion-estimation computer-vision robotics video-processing
No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 15 / 25
Community 6 / 25

How are scores calculated?

Stars

87

Forks

3

Language

Python

License

BSD-3-Clause

Last pushed

Dec 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/msu-video-group/memfof"

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