# Enhance! Super Resolution From Google | Two Minute Papers #124

## Метаданные

- **Канал:** Two Minute Papers
- **YouTube:** https://www.youtube.com/watch?v=WovbLx8C0yA
- **Дата:** 01.02.2017
- **Длительность:** 4:19
- **Просмотры:** 88,763
- **Источник:** https://ekstraktznaniy.ru/video/14718

## Описание

The paper "RAISR: Rapid and Accurate Image Super Resolution" is available here:
https://arxiv.org/abs/1606.01299

Additional supplementary materials: https://drive.google.com/file/d/0BzCe024Ewz8ab2RKUFVFZGJ4OWc/view

Blog posts:
https://research.googleblog.com/2016/11/enhance-raisr-sharp-images-with-machine.html
https://www.blog.google/products/google-plus/saving-you-bandwidth-through-machine-learning/

WE WOULD LIKE TO THANK OUR GENEROUS PATREON SUPPORTERS WHO MAKE TWO MINUTE PAPERS POSSIBLE:
Sunil Kim, Daniel John Benton, Dave Rushton-Smith, Benjamin Kang.
https://www.patreon.com/TwoMinutePapers

Subscribe if you would like to see more of these! - http://www.youtube.com/subscription_center?add_user=keeroyz

Music: Dat Groove by Audionautix is licensed under a Creative Commons Attribution license (https://creativecommons.org/licenses/by/4.0/)
Artist: http://audionautix.com/

Image credits:
Super resolution -
https://en.wikipedia.org/wiki/Super-resolution_imaging
https://commons.wikime

## Транскрипт

### Segment 1 (00:00 - 04:00) []

dear fellow Scholars this is 2minute papers with car what is super resolution is a process where our input is a course low resolution image and the output is the same image but now with more details and in high resolution we'll also refer to this process as image upscaling and in this piece of work we are interested in performing single image super resolution which means that no additional data is presented to the algorithm that could help the process despite the incredible results seen in practically any of the crime solving television shows out there our intuition would perhaps say that this problem for the first sight sounds impossible how could one mathematically feel in the details when these details are completely unknown well that's only kind of true let's not confuse super resolution with image in painting where we essentially cut an entire part out of an image and try to replace it leaning on our knowledge of the surroundings of the missing part that's a different problem here the entirety of the image is known and the details require some enhancing and this particular method is not based on neural networks but is still a learning based technique the cool thing here is that we can use a training data set that is for all intents and purposes arbitrarily large we can just grab a high resolution image convert it to a lower resolution and we immediately have our hands on a training example for the learning algorithm these would be the before and after images if you will and here during learning the image is subdivided into small image patches and buckets are created to aggregate the information between patches that share similar features these features include brightness textures and the orientation of the edges the technique looks at how the small and large resolution images relate to each other when View viewed through the lens of these features two remarkably interesting things arose from this experiment one it outperforms existing neural network based techniques and two it only uses 10,000 images and 1 hour of training time which is in the world of deep neural networks is so little it's completely unheard of insanity really well done some tricks are involved to keep the memory consumption low the paper discusses how it is done and there are also plenty of other details within make sure to have a look as always it is linked in the video description it can either be run directly on the low resolution image or alternatively we can first run a cheap and naive decade old upscaling algorithm and run this technique on the upscaled output to improve it note that super resolution is a remarkably competitive field of research there are hundreds and hundreds of papers appearing on this every year and almost every single one of them seems to be miles ahead of the previous ones where in reality the truth is that most of these methods have different weaknesses and strengths and so far I haven't seen any technique that would be viable for Universal use to make sure that a large number of cases is covered the authors posted a sizable supplementary document with comparisons this gives so much more Credence to the results I am hoping to see a more widespread adoption of this in future papers in this area for now when viewing websites I feel that we are close to the point where we could choose to transmit only the lower resolution images through the network and perform super resolution on them locally on our phones and computers this will lead to significant savings on network bandwidth we are living amazing times indeed if you are enjoying the series make sure to subscribe to the channel or you can also pick up really cool perks on our patreon page through this icon with the letter P thanks for watching and for your generous support and I'll see you next time