Srameo/LED

[ICCV 2023] Lighting Every Darkness in Two Pairs: A Calibration-Free Pipeline for RAW Denoising && [Arxiv 2023] Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Model && [NeurIPS 2025] UltraLED: Learning to See Everything in Ultra-High Dynamic Range Scenes

48
/ 100
Emerging

This project helps photographers and image processing professionals transform dark, noisy RAW camera images into clear, high-quality pictures. It takes your underexposed RAW photos as input and produces images with significantly reduced noise and improved clarity, without requiring complex camera calibration. Image technicians, forensic photographers, or anyone working with challenging low-light photography would use this tool.

400 stars.

Use this if you need to quickly denoise RAW images taken in extremely low-light conditions, especially when traditional noise model calibration is too time-consuming or impractical.

Not ideal if you primarily work with already-processed JPEG or other non-RAW image formats, as it's specifically designed for RAW denoising.

low-light photography image denoising RAW image processing digital photography computational imaging
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

400

Forks

39

Language

Python

License

Last pushed

Dec 17, 2025

Commits (30d)

0

Get this data via API

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

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