KentuckY Error Modeler

KEMY is based on KREMY (KentuckY Raw Error Modeler, pronounced "creamy") is a free software tool created to improve the quality of raw image captures -- potentially simultaneously improving SNR and resolution. The interesting thing is how KEMY works: it isn't using deep learning nor any of the traditional image denoising nor sharpening methods. Instead, it begins by creating a model bounding pixel value errors. It then uses the captured pixel values as initial estimates of the true scene values while applying texture synthesis to refine pixel values to be more contextually-consistent -- without violating any of the computed pixel error bounds. Put simply, iteratively refining pixel values to be consistent with more constraints tends to converge toward the true pixel values.

Although KEMY works well, it is painfully slow, and thus has not been formally published upon nor released. There is a version of KEMY's logic in the KAMF postkamf program -- which is fine because KAMF images are just 640x480 pixels, so processing speed is quite acceptable for KAMF.

Some files for this work in progress:

• The kemy.cpp source code and CMakeLists.txt
• Here is a sample image (DPReview test scene) and the KEMY-improved version:
  
  Click on the above images to see the full resolution. The bad news is that KEMY took about 8 minutes of CPU time to do that.
• Logically, KREMY and KEMY are closely related to Non-Local Means Denoising. There are many implementations of NLM, including in OpenCV. Here's one in scikit-image.