trougnouf / nind-denoise Goto Github PK

there is a syntax error:

File "", line 1
(ybatch.shape=)
^
SyntaxError: invalid syntax

The current dataset are photos fixed at certain exposure/saturation/contrast. Different photographers will have different "flavor/taste" and will process the RAW differently, low vs high contrast or saturation, even the white balance will also be different, some will prefer warm tone, some might prefer leaving the original color cast (e.g. LED lighting, ...)

What would be a good strategy in terms of training data? I can do exposure bracketing in RAW, but then how should I process the RAW into sample data? Will a naive approach of exporting the RAW at different WB, contrast, saturation, ... work? Is it even possible to train on the unprocessed RAW (perhaps 12-bit demosaiced)?

The step of taking bracketed shots is probably the same regardless of how the RAW would be processed and trained, so maybe I can just start shooting samples. Have you found a place to host sample? For sharing, we can store only the original RAW files, 25-30MB each, about 30MB x 5EV = 150MB for each set, 15GB for 100 samples, not too bad while still maintaining the flexibility should we want to change the training approach. Those who run the training can do the processing/exporting locally.

Just a place to share links to datasets.

X-T2, fixed at ISO200, 7 shots per set, 1EV per step:
https://drive.google.com/drive/folders/1ZLrDLV6V-EBcGv1MbCl_UtQkGi7Tjvs2

Hi, I'm experimenting with building a small NCNN or TFLite based CLI tool based on your excellent work here.

Unfortunately I don't see license information in the repository.
Could you clarify the license under which you offer the code and your pretrained models?

Added an initial version of ECC alignment algorithm. Not sure how you're planning on feeding the images for training so I'm not putting too much thought into its parameters yet. The default termination epsilon of 0.01 and 50 iterations seem to work fine. OpenEXR is still a pain due to security issues around it.

master...hqhoang:nind-denoise:align-images