[dharma1]

http://halide-lang.org/ is pretty good at optimising image filters for realtime use on mobile devices.

What neural networks are really good at, is if feature engineering the transform is difficult or time consuming. Like upscaling resolution (SRGAN) - or increasing dynamic range of LDR images by training with LDR-HDR pairs would be another nice use case. Neural nets for processing 1080p+ images have too many parameters to run well on mobile devices, but looks like this research gets around that (for some use cases).

Will have to play with the repo!

Film emulation (beyond the usual 3D LUTs for colour matching film stock) would be a fun use case. Wonder how much training data is required

[web007]

Film emulation sounds like a special case of style transfer. Those run from a single image, so it might be reasonable to emulate it with very little data.

[dharma1]

I think accurate film emulation would require a fair amount of training material pairs (digital/film) to learn the transformation between colours, colour/scene dependent dynamic range compression, and other artefacts like local contrast. The paper mentions using 4000 training pairs for their HDR+ example

[computerex]

They don't process the whole 1080p image, they down sample it to 256x256.