• Stars
    star
    308
  • Rank 135,712 (Top 3 %)
  • Language
    Python
  • License
    MIT License
  • Created almost 6 years ago
  • Updated over 1 year ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

A simple and light-weight camera image processing pipeline

simple-camera-pipeline

A simple and light-weight camera image signal processor (ISP) pipeline implemented in MATLAB and Python.

Stages currently included in the pipeline:

  • Normalization
  • Lens shading correction (Python only)
  • White balance
  • Demosaicing
  • Color space transformation (CIE XYZ)
  • Color space transformation (sRGB)
  • Gamma correction
  • Global tone mapping

Start by running:

Matlab: matlab/demo.m

Python:

python/demo1.py

python/demo2.py

Python requirements (python/requirements.txt) -- other versions may work

numpy==1.17.2
scipy==1.3.1
opencv-python==4.1.1.26
rawpy==0.14.0
exifread==2.1.2
colour-demosaicing==0.1.5

This is the code used to render the sRGB images from the Raw-RGB images of the Smartphone Image Denoising Dataset (SIDD).

This code is helpful for participants of the real image denoising challenges on CodaLab:

NTIRE 2020 Real Image Denoising Challenge - Track 1: rawRGB

NTIRE 2020 Real Image Denoising Challenge - Track 2: sRGB

NTIRE 2019 Real Image Denoising Challenge - Track 1: Raw-RGB

NTIRE 2019 Real Image Denoising Challenge - Track 2: sRGB

Paper

Abdelhamed, A., Lin, S., & Brown, M. S. (2018). A High-Quality Denoising Dataset for Smartphone Cameras. In 2018 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition. {IEEE}. Retrieved from https://doi.org/10.1109%2Fcvpr.2018.00182

Enjoy!