Repository files navigation

As told by its name, fast-openISP is afaster (and bugs-fixed) re-implementation oftheopenISP project.

Compared to C-style code in the official openISP repo, fast-openISP uses pure matrix implementations based on Numpy, andincreases processing speedover 300 times.

Here is the running time in my Ryzen 7 1700 8-core 3.00GHz machine with the 1920x1080 input Bayer array:

^* CEH module is not included in the official openISP pipeline.

Clone this repo and run

python demo.py

The ISP outputs will be saved to./output directory.

The only required package for pipeline execution isnumpy.opencv-python andscikit-image are required only fordata IO.

All modules in fast-openISPreproduceprocessing algorithmsin openISP, except for EEH and BCC modules. In addition, a CEH (contrast enhancement) module withCLAHE isadded into the fast-openISP pipeline.

The official openISP usesanasymmetric kernelto extract edge map. In fast-openISP, however, we use the subtraction between the original and the gaussian filteredY-channel as the edge estimation, which reduces the artifact when the enhancement gain is large.

The official openISP enhances the image contrast by pixel-wise enlarging the difference between pixel values and aconstant integer (128). In fast-openISP, we use the median value of the whole frame instead of a constant.

Tunable parameters in fast-openISP are differently named from those in openISP, but they are all self-explained,and no doubt you can easily tell the counterparts in two repos. All parameters are managed in a yamlin./configs, one file per camera.

Bayer Input

CFA Interpolation

Color Correction

Gamma Correction

Non-local Means & Bilateral Filter

Contrast Enhancement

Edge Enhancement

Hue & Saturation Control

Brightness & Contrast Control

Copyright 2021 Qiu Jueqin.

Licensed underMIT.