Re:Image Scaling using Deep Convolutional Neural Networks
by buymorechuck on Thursday August 20, 2015 @07:51PM
(#10095273)
There are several examples in the article that show original, bicubic and DeCNN upscaling side by side for comparison.
[ Parent
| on HN ]
Re:Image Scaling using Deep Convolutional Neural Networks
by rasz_pl on Thursday August 20, 2015 @08:12PM
(#10095329)
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
by larsiusprime on Thursday August 20, 2015 @10:58PM
(#10095761)
waifu2x is based on the same basic principle as this, and it beats the pants off of those algorithms, for the kind of images its best at (waifu2x was designed for, and therefore trained on, anime/manga images)
Re:Image Scaling using Deep Convolutional Neural Networks
by buymorechuck on Friday August 21, 2015 @12:00AM
(#10095908)
FWIW, waifu2x was inspired by this paper from researchers at Chinese University of Hong Kong and Microsoft Research Asia http://arxiv.org/abs/1501.00092v3
waifu2x is a great demonstration of this approach applied to a specific domain.
By coincidence, Flipboard's DNN approach was developed around the same time as the MSRA research in summer 2014.
I'm excited to see future research in applying deep learning to generative tasks. Some of the CNN music composition work is quite impressive.