Human image synthesis

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search
An image generated by StyleGAN, a generative adversarial network (GAN), that looks deceptively like a portrait of a young woman. This image was generated by an artificial intelligence based on an analysis of portraits.
An image generated by StyleGAN, a generative adversarial network (GAN), that looks deceptively like a portrait of a young woman. This image was generated by an artificial intelligence based on an analysis of portraits.
In this morph target animation system four "expressions" have been defined as deformations of the geometry of the model. Any combination of these four expressions can be used to animate the mouth shape. Similar controls can be applied to animate an entire human-like model.

Human image synthesis is technology that can be applied to make believable and even photorealistic renditions[1][2] of human-likenesses, moving or still. It has effectively existed since the early 2000s. Many films using computer generated imagery have featured synthetic images of human-like characters digitally composited onto the real or other simulated film material. Towards the end of the 2010s deep learning artificial intelligence has been applied to synthesize images and video that look like humans, without need for human assistance, once the training phase has been completed, whereas the old school 7D-route required massive amounts of human work.

Timeline of human image synthesis[edit]

BRDF vs. subsurface scattering inclusive BSSRDF i.e. Bidirectional scattering-surface reflectance distribution function
  • Since September 1 2019 Texas senate bill SB 751 amendments to the election code came into effect, giving candidates in elections a 30-day protection period to the elections during which making and distributing digital look-alikes or synthetic fakes of the candidates is an offense. The law text defines the subject of the law as "a video, created with the intent to deceive, that appears to depict a real person performing an action that did not occur in reality"[22]
  • In September 2019 Yle, the Finnish public broadcasting company, aired a result of experimental journalism, a deepfake of the President in office Sauli Niinistö in its main news broadcast for the purpose of highlighting the advancing disinformation technology and problems that arise from it.

Key breakthrough to photorealism: reflectance capture[edit]

ESPER LightCage is an example of a spherical light stage with multi-camera setup around the sphere suitable for capturing into a 7D reflectance model.

In 1999 Paul Debevec et al. of USC did the first known reflectance capture over the human face with their extremely simple light stage. They presented their method and results in SIGGRAPH 2000.[4]

Bidirectional scattering distribution function (BSDF) for human skin likeness requires both BRDF and special case of BTDF where light enters the skin, is transmitted and exits the skin.

The scientific breakthrough required finding the subsurface light component (the simulation models are glowing from within slightly) which can be found using knowledge that light that is reflected from the oil-to-air layer retains its polarization and the subsurface light loses its polarization. So equipped only with a movable light source, movable video camera, 2 polarizers and a computer program doing extremely simple math and the last piece required to reach photorealism was acquired.[4]

For a believable result both light reflected from skin (BRDF) and within the skin (a special case of BTDF) which together make up the BSDF must be captured and simulated.



The whole process of making digital look-alikes i.e. characters so lifelike and realistic that they can be passed off as pictures of humans is a very complex task as it requires photorealistically modeling, animating, cross-mapping, and rendering the soft body dynamics of the human appearance.

Synthesis with an actor and suitable algorithms is applied using powerful computers. The actor's part in the synthesis is to take care of mimicking human expressions in still picture synthesizing and also human movement in motion picture synthesizing. Algorithms are needed to simulate laws of physics and physiology and to map the models and their appearance, movements and interaction accordingly.

Often both physics/physiology based (i.e. skeletal animation) and image-based modeling and rendering are employed in the synthesis part. Hybrid models employing both approaches have shown best results in realism and ease-of-use. Morph target animation reduces the workload by giving higher level control, where different facial expressions are defined as deformations of the model, which facial allows expressions to be tuned intuitively. Morph target animation can then morph the model between different defined facial expressions or body poses without much need for human intervention.

Using displacement mapping plays an important part in getting a realistic result with fine detail of skin such as pores and wrinkles as small as 100 µm.

Machine learning approach[edit]

In the late 2010s, machine learning, and more precisely generative adversarial networks (GAN), were used by NVIDIA to produce random yet photorealistic human-like portraits. The system, named StyleGAN, was trained on a database of 70,000 images from the images depository website Flickr. The source code was made public on GitHub in 2019[27]. Outputs of the generator network from random input were made publicly available on a number of websites [28][29].

Similarly, since 2018, deepfake technology has allowed GANs to swap faces between actors; combined with the ability to fake voices, GANs can thus generate fake videos that seem convincing.[30]


Main applications fall within the domains of stock photography, synthetic datasets, virtual cinematography, computer and video games and covert disinformation attacks[31][32].

Furthermore, some research suggests that it can have therapeutic effects as "psychologists and counselors have also begun using avatars to deliver therapy to clients who have phobias, a history of trauma, addictions, Asperger’s syndrome or social anxiety."[33] The strong memory imprint and brain activation effects caused by watching a digital look-alike avatar of yourself is dubbed the doppelgänger effect.[33] The doppelgänger effect can heal when covert disinformation attack is exposed as such to the targets of the attack.

Related issues[edit]

The speech synthesis has been verging on being completely indistinguishable from a recording of a real human's voice since the 2016 introduction of the voice editing and generation software Adobe Voco, a prototype slated to be a part of the Adobe Creative Suite and DeepMind WaveNet, a prototype from Google.[34] Ability to steal and manipulate other peoples voices raises obvious ethical concerns. [35]

At the 2018 Conference on Neural Information Processing Systems (NeurIPS) researchers from Google presented the work 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis', which transfers learning from speaker verification to achieve text-to-speech synthesis, that can be made to sound almost like anybody from a speech sample of only 5 seconds (listen). [36]

Sourcing images for AI training raises a question of privacy as people who are used for training didn't consent[37].

Digital sound-alikes technology found its way to the hands of criminals as in 2019 Symantec researchers knew of 3 cases where technology has been used for crime.[38][39]

This coupled with the fact that (as of 2016) techniques which allow near real-time counterfeiting of facial expressions in existing 2D video have been believably demonstrated increases the stress on the disinformation situation.[11]

See also[edit]


  1. ^ Physics-based muscle model for mouth shape control on IEEE Explore (requires membership)
  2. ^ Realistic 3D facial animation in virtual space teleconferencing on IEEE Explore (requires membership)
  3. ^ "Images de synthèse : palme de la longévité pour l'ombrage de Gouraud".
  4. ^ a b c Debevec, Paul (2000). "Acquiring the reflectance field of a human face". Proceedings of the 27th annual conference on Computer graphics and interactive techniques - SIGGRAPH '00. ACM. pp. 145–156. doi:10.1145/344779.344855. ISBN 978-1581132083. Retrieved 2017-05-24.
  5. ^ Pighin, Frédéric. "Siggraph 2005 Digital Face Cloning Course Notes" (PDF). Retrieved 2017-05-24.
  6. ^ In this TED talk video at 00:04:59 you can see two clips, one with the real Emily shot with a real camera and one with a digital look-alike of Emily, shot with a simulation of a camera - Which is which is difficult to tell. Bruce Lawmen was scanned using USC light stage 6 in still position and also recorded running there on a treadmill. Many, many digital look-alikes of Bruce are seen running fluently and natural looking at the ending sequence of the TED talk video.
  7. ^ ReForm - Hollywood's Creating Digital Clones (youtube). The Creators Project. 2017-05-24.
  8. ^ Debevec, Paul. "Digital Ira SIGGRAPH 2013 Real-Time Live". Retrieved 2017-05-24.
  9. ^ "Scanning and printing a 3D portrait of President Barack Obama". University of Southern California. 2013. Retrieved 2017-05-24.
  10. ^ Giardina, Carolyn (2015-03-25). "'Furious 7' and How Peter Jackson's Weta Created Digital Paul Walker". The Hollywood Reporter. Retrieved 2017-05-24.
  11. ^ a b Thies, Justus (2016). "Face2Face: Real-time Face Capture and Reenactment of RGB Videos". Proc. Computer Vision and Pattern Recognition (CVPR), IEEE. Retrieved 2017-05-24.
  12. ^ Suwajanakorn, Supasorn; Seitz, Steven; Kemelmacher-Shlizerman, Ira (2017), Synthesizing Obama: Learning Lip Sync from Audio, University of Washington, retrieved 2018-03-02
  13. ^ Roettgers, Janko (2018-02-21). "Porn Producers Offer to Help Hollywood Take Down Deepfake Videos". Variety. Retrieved 2018-02-28.
  14. ^ Takahashi, Dean (2018-03-21). "Epic Games shows off amazing real-time digital human with Siren demo". VentureBeat. Retrieved 2018-09-10.
  15. ^ Kuo, Lily (2018-11-09). "World's first AI news anchor unveiled in China". Retrieved 2018-11-09.
  16. ^ Hamilton, Isobel Asher (2018-11-09). "China created what it claims is the first AI news anchor — watch it in action here". Retrieved 2018-11-09.
  17. ^ Harwell, Drew (2018-12-30). "Fake-porn videos are being weaponized to harass and humiliate women: 'Everybody is a potential target'". The Washington Post. Retrieved 2019-03-14. In September [of 2018], Google added “involuntary synthetic pornographic imagery” to its ban list
  18. ^ "NVIDIA Open-Sources Hyper-Realistic Face Generator StyleGAN". 2019-02-09. Retrieved 2019-10-03.
  19. ^ a b Paez, Danny (2019-02-13). "This Person Does Not Exist Is the Best One-Off Website of 2019". Inverse (website). Retrieved 2018-03-05.
  20. ^ "New state laws go into effect July 1".
  21. ^ a b "§ 18.2-386.2. Unlawful dissemination or sale of images of another; penalty". Virginia. Retrieved 2020-01-01.
  22. ^ "Relating to the creation of a criminal offense for fabricating a deceptive video with intent to influence the outcome of an election". Texas. 2019-06-14. Retrieved 2020-01-02. In this section, "deep fake video" means a video, created with the intent to deceive, that appears to depict a real person performing an action that did not occur in reality
  23. ^ Johnson, R.J. (2019-12-30). "Here Are the New California Laws Going Into Effect in 2020". KFI. iHeartMedia. Retrieved 2020-01-01.
  24. ^ Mihalcik, Carrie (2019-10-04). "California laws seek to crack down on deepfakes in politics and porn". CNET. Retrieved 2019-10-14.
  25. ^ "China seeks to root out fake news and deepfakes with new online content rules". Reuters. 2019-11-29. Retrieved 2019-12-08.
  26. ^ Statt, Nick (2019-11-29). "China makes it a criminal offense to publish deepfakes or fake news without disclosure". The Verge. Retrieved 2019-12-08.
  27. ^ Synced (2019-02-09). "NVIDIA Open-Sources Hyper-Realistic Face Generator StyleGAN". Synced. Retrieved 2020-08-04.
  28. ^ StyleGAN public showcase website
  29. ^ Porter, Jon (2019-09-20). "100,000 free AI-generated headshots put stock photo companies on notice". The Verge. Retrieved 2020-08-07.
  30. ^ "What Is a Deepfake?". March 2020. Retrieved 8 June 2020.
  31. ^ Harwell, Drew. "Dating apps need women. Advertisers need diversity. AI companies offer a solution: Fake people". Washington Post. Retrieved 2020-08-04.
  32. ^ Porter, Jon (2019-09-20). "100,000 free AI-generated headshots put stock photo companies on notice". The Verge. Retrieved 2020-08-07.
  33. ^ a b Murphy, Samantha (2011). "Scientific American: Your Avatar, Your Guide" (.pdf). Scientific American / Uni of Stanford. Retrieved 2013-06-29.
  34. ^ "WaveNet: A Generative Model for Raw Audio". 2016-09-08. Retrieved 2017-05-24.
  35. ^ "Adobe Voco 'Photoshop-for-voice' causes concern". BBC. 2016-11-07. Retrieved 2016-07-05.
  36. ^ Jia, Ye; Zhang, Yu; Weiss, Ron J. (2018-06-12), "Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis", Advances in Neural Information Processing Systems, 31: 4485–4495, arXiv:1806.04558, Bibcode:2018arXiv180604558J
  37. ^ Business, Rachel Metz, CNN. "If your image is online, it might be training facial-recognition AI". CNN. Retrieved 2020-08-04.
  38. ^ "Fake voices 'help cyber-crooks steal cash'". BBC. 2019-07-08. Retrieved 2020-04-16.
  39. ^ Drew, Harwell (2020-04-16). "An artificial-intelligence first: Voice-mimicking software reportedly used in a major theft". Washington Post. Retrieved 2019-09-08.