Artisto: Difference between revisions

From Wikipedia, the free encyclopedia
Browse history interactively
← Previous editNext edit →
Content deleted Content added
VisualWikitext
m →‎Technology: arxivify URL / redundant url using AWB
m →‎Technology: Various citation & identifier cleanup, plus AWB genfixes (arxiv version pointless when published)
Line 47: Line 47:


== Technology ==
== Technology ==
The idea of transferring styles from the works by famous artists to images was first mentioned in September 2015 after the publication of Leon Gatys's article "A Neural Algorithm of Artistic Style",<ref name="Neural">{{cite journal |vauthors=Gatys LA, Ecker AS, Bethge M | title=A Neural Algorithm of Artistic Style| arxiv=1508.06576v2 | journal = Computer Vision and Pattern Recognition| volume = | issue = | pages = 16 | date = August 26, 2015 | pmid = | doi = | publisher = | location = }}</ref> where he described the algorithm in detail. The major shortcoming of this algorithm is its slow performance, which is up to dozens of seconds depending on the algorithm's settings.
The idea of transferring styles from the works by famous artists to images was first mentioned in September 2015 after the publication of Leon Gatys's article "A Neural Algorithm of Artistic Style",<ref name="Neural">{{cite journal |vauthors=Gatys LA, Ecker AS, Bethge M | title=A Neural Algorithm of Artistic Style| arxiv=1508.06576 | journal = Computer Vision and Pattern Recognition| volume = | issue = | pages = 16 | date = August 26, 2015 | pmid = | doi = | publisher = | location = }}</ref> where he described the algorithm in detail. The major shortcoming of this algorithm is its slow performance, which is up to dozens of seconds depending on the algorithm's settings.


In March 2016, Russian researcher Dmitry Ulyanov's article was published, where he invented a way to improve the generation of stylized pictures using additional neuron generator network training.<ref name="Texture">{{cite journal |vauthors=Ulyanov D, Lebedev V, Vedaldi A, Lempitsky V | title=Texture Networks: Feed-forward Synthesis of Textures and Stylized Images| url=https://arxiv.org/pdf/1603.03417v1.pdf | journal = Computer Vision and Pattern Recognition| volume= | issue= | pages=10 | date= March 10, 2016 | pmid = | doi = | publisher = | location = }}</ref> With this approach, stylized images can be generated within just dozens of milliseconds. Seventeen days after Ulyanov's article, Justin Johnson published an article containing an identical idea,<ref name="Perceptual">{{cite journal |vauthors=Ulyanov D, Johnson J, Alahi A, Fei-Fei L | title=Perceptual Losses for Real-Time Style Transfer and Super-Resolution| url=https://arxiv.org/pdf/1603.08155.pdf | journal = Computer Vision and Pattern Recognition| volume = | issue = | pages = 18 | date = March 27, 2016 | pmid = | doi = | publisher =Department of Computer Science, Stanford University | location = }}</ref> the only difference being the structure of the generator network.
In March 2016, Russian researcher Dmitry Ulyanov's article was published, where he invented a way to improve the generation of stylized pictures using additional neuron generator network training.<ref name="Texture">{{cite journal |vauthors=Ulyanov D, Lebedev V, Vedaldi A, Lempitsky V | title=Texture Networks: Feed-forward Synthesis of Textures and Stylized Images| url=https://arxiv.org/pdf/1603.03417v1.pdf | journal = Computer Vision and Pattern Recognition| volume= | issue= | pages=10 | date= March 10, 2016 | pmid = | doi = | publisher = | location = }}</ref> With this approach, stylized images can be generated within just dozens of milliseconds. Seventeen days after Ulyanov's article, Justin Johnson published an article containing an identical idea,<ref name="Perceptual">{{cite journal |vauthors=Ulyanov D, Johnson J, Alahi A, Fei-Fei L | title=Perceptual Losses for Real-Time Style Transfer and Super-Resolution| url=https://arxiv.org/pdf/1603.08155.pdf | journal = Computer Vision and Pattern Recognition| volume = | issue = | pages = 18 | date = March 27, 2016 | pmid = | doi = | publisher =Department of Computer Science, Stanford University | location = }}</ref> the only difference being the structure of the generator network.

Revision as of 18:06, 21 May 2019

Artisto
Original author(s)Mail.ru Group
Developer(s)Mail.ru Group
Initial release29 July 2016; 7 years ago (2016-07-29)
Stable release
1.4 / 19 August 2016; 7 years ago (2016-08-19)
Operating systemiOS 8.0 or later;[1]
Android 4.1 or later;[2]
Available inEnglish, Russian
TypeVideo
LicenseFreeware
Websiteartisto.my.com

Artisto is a video processing application with art and movie effects filters based on neural network algorithms created in 2016 by Mail.ru Group machine learning specialists.

At the moment the application can process videos up to 10 seconds long[3] and offers users 21 filters,[4][5] including those based on the works of famous artists (e.g. Blue Dream — Pablo Picasso), theme-based (Rio-2016 — related to the 2016 Summer Olympics in Rio de Janeiro) and others. The app works with both pre-recorded videos and videos recorded with the application.

History

Information on the application first appeared on Mail.ru Group Vice President Anna Artamonova's FB page on July 29, 2016.[6] At the moment of posting there was only an Android version available. According to Anna, the application's first version only took eight days to develop. On July 31 the application was added to the AppStore for free download.[7]

From this moment and continuing on into the present, Artisto has been the world’s first app that uses neural networks for editing short videos, processing them in the style of famous artworks or any other source image.[8] Prisma (app) application developers promise to deliver similar functionality at any moment.[9]

The application soon won recognition and started to attract the attention of both international brands (e.g. Korean auto manufacturer Kia Motors) and popular singers and musicians.[10]

According to the independent App Annie analysis system, within the first two weeks on the market the application made it onto TOP download lists in nine countries.[11]

Technology

The idea of transferring styles from the works by famous artists to images was first mentioned in September 2015 after the publication of Leon Gatys's article "A Neural Algorithm of Artistic Style",[12] where he described the algorithm in detail. The major shortcoming of this algorithm is its slow performance, which is up to dozens of seconds depending on the algorithm's settings.

In March 2016, Russian researcher Dmitry Ulyanov's article was published, where he invented a way to improve the generation of stylized pictures using additional neuron generator network training.[13] With this approach, stylized images can be generated within just dozens of milliseconds. Seventeen days after Ulyanov's article, Justin Johnson published an article containing an identical idea,[14] the only difference being the structure of the generator network.

The Artisto application was developed using these open-source technologies, which Mail.ru Group's machine learning specialists improved for faster video processing and better quality.[15]

References

  1. ^ "Artisto – Video Editor with Unique Art Filters and Movie Effects". Itunes.apple.com. 2016-07-31. Retrieved 2016-08-23.
  2. ^ "Artisto Video Editor with Unique Art Filters and Mo..." play.google.com. 2016-07-29. Retrieved 2016-08-23.
  3. ^ "Artisto app is like Prisma for video, turning videos into instant art". mashable.com. 2016-08-06. Retrieved 2016-08-23.
  4. ^ Ivan Mehta (2016-08-10). "Meet Prisma's Competitors In Photos And Video: Alter And Artisto". huffingtonpost.in. Retrieved 2016-08-23.
  5. ^ Uzair Ahmad (2016-08-14). "Give Artistic look like Prisma to your Videos using Artisto Android App". teamandroid.com. Retrieved 2016-08-23.
  6. ^ "Mail.Ru Group разработал аналог Prisma для обработки видео". kommersant.ru. 2016-07-29. Retrieved 2016-08-23.
  7. ^ "Artisto transforms your videos into moving paintings". engadget.com. 2016-08-03. Retrieved 2016-08-23.
  8. ^ Onsa Mustafa (2016-08-10). "Artisto- A Video Editing App Uses Neural Network Similar to Prisma". phoneworld.com.pk. Retrieved 2016-08-23.
  9. ^ Mark Melin (2016-07-27). "Prisma App's Video Editing Feature Coming Soon To Android, iOS". valuewalk.com. Retrieved 2016-08-23.
  10. ^ "On the steps of Prisma: Mail.Ru Group applies neural network technologies to videos". ewdn.com. 2016-08-04. Retrieved 2016-08-23.
  11. ^ "Artisto – Video Editor with Unique Art Filters and Movie Effects". appannie.com. 2016-07-30. Retrieved 2016-08-23.
  12. ^ Gatys LA, Ecker AS, Bethge M (August 26, 2015). "A Neural Algorithm of Artistic Style". Computer Vision and Pattern Recognition: 16. arXiv:1508.06576.
  13. ^ Ulyanov D, Lebedev V, Vedaldi A, Lempitsky V (March 10, 2016). "Texture Networks: Feed-forward Synthesis of Textures and Stylized Images" (PDF). Computer Vision and Pattern Recognition: 10.
  14. ^ Ulyanov D, Johnson J, Alahi A, Fei-Fei L (March 27, 2016). "Perceptual Losses for Real-Time Style Transfer and Super-Resolution" (PDF). Computer Vision and Pattern Recognition. Department of Computer Science, Stanford University: 18.
  15. ^ "Mail.ru launches video-filter app Aristo to compete with Prisma". venturebeat.com. 2016-08-06. Retrieved 2016-08-23.

External links

Retrieved from "https://en.wikipedia.org/w/index.php?title=Artisto&oldid=898148966"