lingyzhu0101/UDU

[ECCV'24] Unrolled Decomposed Unpaired Learning for Controllable Low-Light Video Enhancement

29
/ 100
Experimental

This project helps video editors, content creators, and surveillance professionals improve the quality of videos recorded in low-light conditions. It takes dark, noisy video footage and enhances its brightness, reduces noise, and ensures smooth transitions between frames. The result is clearer, more consistent video that's easier to view and analyze.

No commits in the last 6 months.

Use this if you need to transform poorly lit video recordings into visibly clear and temporally stable footage, especially when you don't have a perfectly lit 'before' and 'after' example to train with.

Not ideal if you are working with still images rather than videos, or if your primary need is complex object recognition rather than general video enhancement.

video-editing video-production surveillance-footage dark-scene-enhancement content-creation
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

13

Forks

3

Language

Python

License

Last pushed

May 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/lingyzhu0101/UDU"

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