Deep Bilateral Learning for Real-Time Image Enhancement
groups.csail.mit.edu
Deep Bilateral Learning for Real-Time Image Enhancement
1–10 of 20 posts
Re: Deep Bilateral Learning for Real-Time Image Enhancement
#2Link to github repo is 404'ing (https://github.com/google/hdrnet)
Re: Deep Bilateral Learning for Real-Time Image Enhancement
#3"Enhancement" meaning tone-mapping? Are neural networks really required for that? Seems like a lot of heavy machinery for the resulting filter, but maybe tone-mapping standards have gone up.
Re: Deep Bilateral Learning for Real-Time Image Enhancement
#4this is the most complicated histo-stretch I've ever seen
Re: Deep Bilateral Learning for Real-Time Image Enhancement
#5"Enhancement" meaning tone-mapping? Are neural networks really required for that? Seems like a lot of heavy machinery for the resulting filter, but maybe tone-mapping standards have gone up.
They imply "human operator" level retouching, so potentially some combination of tone mapping, unsharp mask, edge enhancement, etc. as a single NN operation. It's also <30ms for 1080p on mobile, so potentially better than average speed.
Re: Deep Bilateral Learning for Real-Time Image Enhancement
#6http://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
Re: Deep Bilateral Learning for Real-Time Image Enhancement
#7http://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 paramete…
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.
Re: Deep Bilateral Learning for Real-Time Image Enhancement
#8Buried lead is the awesome demo - https://youtu.be/GAe0qKKQY_I?t=130
Re: Deep Bilateral Learning for Real-Time Image Enhancement
#9http://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 paramete…
They don't process the whole 1080p image, they down sample it to 256x256.
Re: Deep Bilateral Learning for Real-Time Image Enhancement
#10Buried lead is the awesome demo - https://youtu.be/GAe0qKKQY_I?t=130
I really would like to see them try different learning sets that vary the "styles" of retouching. This example looks like it's strongly biased to the "make the images pop!" style of retouching, blowing highlights, shadows and contrasts.
What if the input set has more subtle retouching that pulls highlights and pushes shadows, but without the aforementioned issues?
What if they got their hands on the unedited and edited magnum photos? That would produce an interesting B&W filter, for sure!
https://www.slrlounge.com/magnum-photos-darkroom-magic-genes...