# Deep Image Prior | Two Minute Papers #219 ## Метаданные - **Канал:** Two Minute Papers - **YouTube:** https://www.youtube.com/watch?v=_BPJFFkxSbw - **Дата:** 10.01.2018 - **Длительность:** 5:00 - **Просмотры:** 33,344 - **Источник:** https://ekstraktznaniy.ru/video/14531 ## Описание The paper "Deep Image Prior" and its source code is available here: https://dmitryulyanov.github.io/deep_image_prior Our Patreon page with the details: https://www.patreon.com/TwoMinutePapers One-time payment links are available below. Thank you very much for your generous support! PayPal: https://www.paypal.me/TwoMinutePapers Bitcoin: 13hhmJnLEzwXgmgJN7RB6bWVdT7WkrFAHh Ethereum: 0x002BB163DfE89B7aD0712846F1a1E53ba6136b5A We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Andrew Melnychuk, Brian Gilman, Christian Ahlin, Christoph Jadanowski, Dave Rushton-Smith, Dennis Abts, Emmanuel, Eric Haddad, Esa Turkulainen, Evan Breznyik, Frank Goertzen, Kaben Gabriel Nanlohy, Malek Cellier, Marten Rauschenberg, Michael Albrecht, Michael Jensen, Michael Orenstein, Raul Araújo da Silva, Robin Graham, Steef, Steve Messina, Sunil Kim, Torsten Reil. https://www.patreon.com/TwoMinutePapers Two Minute Papers Merch: US: http://twominutepapers.com/ EU/Worldwid ## Транскрипт ### [] dear fellow Scholars this is 2minute papers with car this work is about performing useful image restoration tasks with a convolutional neural ### JPEG Artifacts removal [0:08] network with an additional twist its main use cases are as follows one in the case of jpeg artifact removal the input is this image with many blocky artifacts that materialized during compression and the output is restored version of this image two image in painting where some ### Inpainting [0:28] regions of the input image are missing and are to be filled with useful and hopefully plausible information three super resolution where the input image ### Super-resolution [0:37] is intact but is very coarse and has low resolution and the output should be a more detailed higher resolution version of the same image this is the classic enhanced scenario from the CSI TV series it is typically hard to do because there is a stupendously large number of possible high resolution image solutions that we could come up with as an output for image Den noising is also a ### Denoising [1:02] possibility the standard way of doing these is that we train such a network on a large database of images so that they can learn the concept of many object classes such as humans animals and more and also the typical features and motives that are used to construct such images these networks have some sort of understanding of these images and hence can perform these operations better than most handcrafted algorithms so let's have a look at some comparisons do you see these bold LED labels that classify these algorithms as trained or untrained the bcbic interpolation is a classic untrained algorithm that almost naively tries to guess the pixel Colors by averaging its neighbors this is clearly untrained because it does not take a database of images to learn on understandably the fact that these results are Le cluster is to show that non-learning based algorithms are not great at this the Sr rest net is a state-of-the-art learning based technique for super resolution that was trained on a large database of input images it is clearly doing way better than by cubic interpolation and look we have this deep prior algorithm that performs comparably well but is labeled to be untrained so what is going on here and here comes the twist this convolutional neural network is actually untrained this means that the neuron weights are randomly initialized which generally leads to completely useless results on most problems so no aspect of this network works through the data it has learned on all the required information is contained within the structure of the network itself we all know that the structure of these neural networks matter a great deal but in this case it is shown that it is at least as important as the training data itself a very interesting and esoteric idea indeed please make sure to have a look at the paper for details as there are many details to be understood to get a more complete view of this conclusion in the comparisons beyond the images researchers often publish this psnr number that you see for each image this is the peak signal to noise ratio which means how close the output image is to the ground truth and this number is of course always subject to maximization remarkably this untrained Network performs well on both images with natural patterns and man-made objects Reconstruction from a pair of Flash and no flash photography images is also a possibility and the algorithm does not contain the light leaks produced by a highly competitive handcrafted algorithm a jointed bilateral filter quite remarkable indeed the supplementary materials and the project website contain a ton of comparisons against competing techniques so make sure to have a look at that if you would like to know more the source code of this project is available under the permissive Apache 2. 0 license if you have enjoyed this episode and feel that eight of these videos a month is worth a dollar please consider supporting us on patreon $1 is almost nothing but it keeps the papers coming recently we have also added the possibility of one-time payments through PayPal and cryptocurrencies I was stunn to see how generous our crypto loving fellow Scholars are since most of these crypto donations are Anonymous and it is not possible to say thank you to everyone individually I would like to say a huge thanks to everyone who supports the series and this applies to everyone regardless of contribution just watching the series and spreading the word is already a great deal of help for us thanks for watching and for your generous support and I'll see you next time