Introducing a new FOSS raw image denoiser, RawRefinery, and seeking testers.

[Popanz (Uli)]

My thoughts:
I have my personal problems with the results of most AI denoising. See here:

Show me how you denoise

The more AI denoising I see, the more critical I get. The results are often astonishing. Regarding noise as well as to it’s plastic look. Just for comparison: if you look at the results (your’s with rawrefinery and mine) zoomed out, they look quite similar: [151A2902_03] Watching at 100% view I simply prefer the overall look of traditional denoising: [151A2902_02] This is not ment as a bashing against RawRefinery, but as some critical thinking and maybe it is just a matter of taste. I sal…

I second @Terry 's answer, that maybe a combination of the results would be a smart way.

Interestingly @sillyxone demonstrated here as well the capabilities of ninddenoise:

Show me how you denoise

Just thought it’s interesting how the neural-network would interpret the feather texture. Sigmoid and exposure in darktable, then fed through nind-denoise (with the new model _257 from daniezest, not sure which dataset it was trained from), and GMIC’s richarsonlucy_deblur (10 iterations). [151A2902]

Comparing it to the result of RawRefinery I prefer the look of ninddenoise. Even though the result here is kept darker and therefore isn’t a fair comparison, but for me, it looks like more details were kept. It still has a somewhat plasticly look, but it’s looks still less artificial compared to most other AI denoising tools

This said, I would anyway welcome FOSS AI denoising capabilities for dt. Unfortunately, ninddenoise and RawRefinery are not made for AMD GPUs.
I tried to run ninddenoise on my PC but it didn’t work. I’ll give RawRefineree a try the next days, if I get it to run on my CPU.