Image Scaling using Deep Convolutional Neural Networks
engineering.flipboard.com
Image Scaling using Deep Convolutional Neural Networks
1–10 of 18 posts
Re: Image Scaling using Deep Convolutional Neural Networks
#2This is very cool! Next in DNN adventures should be a network trained with lots of videos for animating still pictures!
Re: Image Scaling using Deep Convolutional Neural Networks
#3Interesting stuff! It would certainly benefit from a comparison to other super-resolution techniques, e.g.
Glasner et al. "Super-resolution from a single image" Freeman et al. "Example-based super-resolution"
Re: Image Scaling using Deep Convolutional Neural Networks
#4John Resig used a Convnet to upscale japanese prints, waifu2x
http://ejohn.org/blog/using-waifu2x-to-upscale-japanese-prin...
Re: Image Scaling using Deep Convolutional Neural Networks
#5What would have made this article interesting was the examples of different images being scaled.
Re: Image Scaling using Deep Convolutional Neural Networks
#6What would have made this article interesting was the examples of different images being scaled.
There are several examples in the article that show original, bicubic and DeCNN upscaling side by side for comparison.
Re: Image Scaling using Deep Convolutional Neural Networks
#7This is very cool! Next in DNN adventures should be a network trained with lots of videos for animating still pictures!
You might like this paper.
Multi-view Face Detection Using Deep Convolutional
Neural Networks : http://arxiv.org/abs/1502.02766
Re: Image Scaling using Deep Convolutional Neural Networks
#8What would have made this article interesting was the examples of different images being scaled.
There are several examples in the article that show original, bicubic and DeCNN upscaling side by side for comparison.
they arent exactly super convincing, I wouldnt be surprised if something like super2xsai + GS4xHqFilter beat those examples :/
Re: Image Scaling using Deep Convolutional Neural Networks
#9What's intriguing about this is that the output isn't really real. The best place to see this is the bark patterns on the trees in the last 3-way comparison. The output is convincing and yet not quite right. The neural net didn't know, so it guessed plausibly. Keep scaling and I bet you'd see Google inceptionism style dream details slipping in.
Re: Image Scaling using Deep Convolutional Neural Networks
#10I'll admit that I skimmed the article but I have the feeling this CNN didn't learn what they intended it to learn. Looking at the examples shown they started with a full resolution image and applied some downsampling algorithm to get the lower resolution to apply their algorithm to. Their algorithm has learned to undo the downsampling that they applied. This doesn't mean it will perform well on images that haven't been downsampled or images that have been downsampled in a different way.