github 资源, matlab/python ISP

剑客

https://github.com/AbdoKame





camera-pipeline

A simple and light-weight camera image processing pipeline implemented in MATLAB and Python.

Start by running:

Matlab: [color=var(--color-text-link-primary)]matlab/demo.m

Python: [color=var(--color-text-link-primary)]python/demo.py

Python requirements ([color=var(--color-text-link-primary)]python/requirements.txt) -- other versions may work

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

This is the code used to render the sRGB images from the Raw-RGB images of the [color=var(--color-text-link-primary)]Smartphone Image Denoising Dataset (SIDD).

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

[color=var(--color-text-link-primary)]NTIRE 2020 Real Image Denoising Challenge - Track 1: rawRGB

[color=var(--color-text-link-primary)]NTIRE 2020 Real Image Denoising Challenge - Track 2: sRGB

[color=var(--color-text-link-primary)]NTIRE 2019 Real Image Denoising Challenge - Track 1: Raw-RGB

[color=var(--color-text-link-primary)]NTIRE 2019 Real Image Denoising Challenge - Track 2: sRGB

[color=var(--color-text-link-primary)]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 [color=var(--color-text-link-primary)]https://doi.org/10.1109%2Fcvpr.2018.00182

Enjoy!