Prisma
Original author(s)Alexey Moiseenkov, Oleg Poyaganov, Ilya Frolov, Andrey Usoltsev, Aram Hardy
Developer(s)Prisma Labs, Inc.
Initial release11 June 2016 (2016-06-11)
Operating systemiOS 8.0 or later;[1]
Android 4.1 or later;[2]
TypePhoto and video
LicenseFreeware
Websiteprisma-ai.com

Prisma is a photo-editing mobile application that uses neural networks and artificial intelligence to apply artistic effects to transform images.[3]

The app was created by Alexey Moiseenkov (Russian: Алексей Моисеенков), Oleg Poyaganov, Ilya Frolov, Andrey Usoltsev, and Aram Hardy. It was launched in June 2016 as a free mobile app.[4] It debuted on iOS on Apple App Store during the first week of June and it became the leading app at the App Store in Russia and other neighboring countries.[5] A week after its launch, the app received over 7.5 million downloads. It had over 1 million active users as of July 2016.[6][7] On 19 July, 2016, the developer launched a beta version of the app for Android, which the developers closed a few hours later after receiving feedback from users.[8][9] This version was released publicly on 24 July, 2016 on Google Play.[2]

In July 2016, the developer announced a video and virtual reality version of the app was under development.[10][11]

On 7 July, 2017, Prisma launched a new app called Sticky which turns selfies into stickers for sharing to social feeds.[12]

History

The app was created by the team led by Alexey Moiseenkov who also founded the Prisma Labs, based in Sunnyvale, California.[13] Moiseenkov previously worked at Mail.Ru and later resigned from his job to dedicate his time to the development of the app.[14] He has said that the development of the app took one and a half months and the team did not do anything to promote the app.[15]

The algorithm that powers the app is based on the open source programming and algorithms behind DeepArt.[16]

Features

Original image
After being processed by Prisma
An image of a toast sandwich rendered via the Tokyo filter.

Users can upload pictures and select a variety of filters to transform the picture with an artistic effect.[17] At launch, the app offered twenty different filters. Additional filters are added daily. In July 2016, Moiseenkov stated that the app will offer forty filters by the end of the month.[13]

The image rendering takes place in Prisma Labs' servers and uses a neural network with artificial intelligence to add the artistic effect. The result is delivered back to the user's phone.[18] Unlike other photo editing apps, Prisma renders the image by going through different layers and recreating the image rather than inserting a layer over the image.[19]

In August 2016, the iOS version of the app was updated to edit image offline by utilizing the phone's processor for image rendering.[20][21]

Reception

Downloads

One week after its debut on iOS App Store, the app was downloaded over 7.5 million times and received over 1 million active users.[6] It also became the top listed app in Russia and its neighboring countries.[5] In the end of July 2016, it was installed over 12.5 million devices with over 1.5 million active users worldwide.[22] According to App Annie, it was listed in the top 10 apps on the App Store in 77 different countries.[23]

Image of Maynooth University captured through prisma

On the first day of the Android version release, it received over 1.7 million downloads with 50 million pictures processed by the app.[22]

Research and technology

The research paper behind the Prisma App technology is called "A Neural Algorithm of Artistic Style" by Leon Gatys, Alexander Ecker and Matthias Bethge and was presented at the premier machine learning conference: Neural Information Processing Systems (NIPS) in 2015.[24] The technology is an example of a Neural Style Transfer algorithm. This technology used in Prisma was developed independently and before Prisma, and both the university and the company have no affiliation with one another.

Further recent work developed by Stanford University, titled Perceptual Losses for Real-Time Style Transfer and Super-Resolution by Justin Johnson, Alexandre Alahi and Li Fei-Fei, has also been able to create real-time style transfer through video.[25]

The code for the previous papers is available at no charge at GitHub for research purposes.[26]

See also

References

  1. "Prisma – Art Photo Editor with Free Picture Effects & Cool Image Filters for Instagram Pics and Selfies". Itunes.apple.com. Retrieved 19 July 2016.
  2. 1 2 Napier Lopez (24 July 2016). "Prisma is now publicly available on Android". thenextweb.com. The Next Web, Inc. Retrieved 24 July 2016.
  3. Darren Orf (12 July 2016). "Prisma Is a Ludicrous Photo Filter App I Never Knew I Wanted". gizmodo.com. Retrieved 19 July 2016.
  4. Elyse Betters (9 July 2016). "What is Prisma and can it really make your pics look like famous art?". pocket-lint.com. Pocket-lint ltd. Retrieved 19 July 2016.
  5. 1 2 Adrien Henni (28 June 2016). "Prisma becomes top mobile photo app for Russia, hopes to repeat success of Masquerade". venturebeat.com. Retrieved 19 July 2016.
  6. 1 2 Dyllan Furness (19 July 2016). "Incredible AI app can 'repaint' your photos, make them look like they were composed by famous artists". Digital Trends. Retrieved 19 July 2016.
  7. Georige Barrat (18 July 2016). "Is Prisma the craze that'll overtake Pokémon GO? Popular app does something amazing with your pictures". mirror.co.uk. MGN Limited. Retrieved 19 July 2016.
  8. Stan Schroeder (19 July 2016). "Prisma is coming to Android, but there's a way to get it sooner". mashable.com. Retrieved 19 July 2016.
  9. Mat Smith (20 July 2016). "Try Prisma's machine-learned art filters on Android". engadget.com. AOL Inc. Retrieved 20 July 2016.
  10. Adario Strange (12 July 2016). "Prisma's stunning art effects are coming to VR and video". mashable.com. Retrieved 19 July 2016.
  11. Juan Buis (8 July 2016). "This mind-blowing photo app makes Instagram's filters look so lame". thenextweb.com. The Next Web, Inc. Retrieved 19 July 2016.
  12. Lomas, Natasha (6 July 2017). "Prisma's next AI project is a fun selfie sticker maker called Sticky | TechCrunch". Retrieved 2017-07-10.
  13. 1 2 Dmitry Shchepochkin (27 November 2022). "Prisma Labs LinkedIn profile". linkedin.com. Retrieved 19 July 2016.
  14. Cara McGoogan (23 July 2016). "Prisma: The world's coolest new app taking over your Instagram". The Telegraph. Telegraph Media Group Limited. Retrieved 23 July 2016.
  15. Eva Hartog (30 June 2016). "Why Russia's Prisma App Could Take Over the World". The Moscow Times. Retrieved 20 July 2016.
  16. Vincent, James (8 November 2016). "Now you can Facebook Live with Prisma's art filters 4". Theverge.com. The Verge. Retrieved 28 November 2016.
  17. Timothy J. Seppala (24 June 2016). "Neural net photography tweaks go mobile with Prisma on iOS". .engadget.com. AOL Inc. Retrieved 19 July 2016.
  18. Mary-Ann Russon (18 July 2016). "What is Prisma? Behind the hip new app that turns your photos into impressionist paintings using AI". International Business Times. IBTimes Co., Ltd. Retrieved 19 July 2016.
  19. Sam Levin (14 July 2016). "Why everyone is crazy for Prisma, the app that turns photos into works of art". The Guardian. Guardian News and Media Limited. Retrieved 20 July 2016.
  20. Luis D (24 August 2016). "Prisma now works offline, video editing coming soon". Phone Arena. Retrieved 26 August 2016.
  21. Paul Monckton (24 August 2016). "Hugely Successul Prisma iOS App Taken Offline". Forbes. Retrieved 26 August 2016.
  22. 1 2 Paul Monckton (26 July 2016). "A Sneak Peek At Prisma's New Unreleased Features". Forbes. Retrieved 27 July 2016.
  23. Ilya Khrennikov (27 July 2016). "Eastern Europe Spawns Another Viral Hit With Prisma Photo App". Bloomberg. Retrieved 27 July 2016.
  24. Gatys, Leon A.; Ecker, Alexander S.; Bethge, Matthias (2015). "A Neural Algorithm of Artistic Style". arXiv:1508.06576 [cs.CV].
  25. Gatys, Leon A.; Ecker, Alexander S.; Bethge, Matthias (2016). "Perceptual Losses for Real-Time Style Transfer and Super-Resolution". arXiv:1603.08155v1 [cs.CV].
  26. "GitHub - jcjohnson/Fast-neural-style: Feedforward style transfer". GitHub.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.