sniklaus/pytorch-liteflownet

a reimplementation of LiteFlowNet in PyTorch that matches the official Caffe version

48
/ 100
Emerging

This project helps researchers and engineers analyze the motion between two images. It takes in a pair of images and outputs an 'optical flow' map, which visually represents how pixels move from the first image to the second. This is useful for anyone working with video analysis, motion tracking, or computer vision tasks where understanding movement is key.

431 stars. No commits in the last 6 months.

Use this if you need to precisely quantify and visualize pixel movement between two consecutive images, especially in a research or prototyping context.

Not ideal if you need a guaranteed correct, production-ready optical flow solution, as this is a personal reimplementation and may have numerical deviations.

motion-estimation video-analysis computer-vision image-processing robotics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

431

Forks

81

Language

Python

License

GPL-3.0

Last pushed

Jan 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sniklaus/pytorch-liteflownet"

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