mv-lab/AISP

AI Image Signal Processing and Computational Photography. Official library for NTIRE (CVPR) and AIM (ICCV/ECCV) Challenges. You will find Learned ISPs, RAW Restoration-Upsampling-Reconstruction, Image Enhancement, Bokeh rendering and more!

35
/ 100
Emerging

This project helps photographers, imaging scientists, and smartphone manufacturers enhance and restore digital images. It takes raw camera sensor data or degraded images (e.g., noisy, blurry, low-resolution) and outputs high-quality, clear, and visually improved images, including advanced bokeh effects. This tool is for anyone working with digital image processing who needs to improve image fidelity or apply complex photographic effects.

549 stars. No commits in the last 6 months.

Use this if you need to restore degraded RAW camera images, enhance smartphone photos in real-time, or generate realistic multi-lens bokeh effects.

Not ideal if your primary need is for high-level computer vision tasks like object detection or image classification, as this focuses on low-level image processing.

computational photography image enhancement digital imaging photo restoration camera processing
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

549

Forks

60

Language

Jupyter Notebook

License

Last pushed

Mar 05, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/mv-lab/AISP"

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