GMU:Procedural Cut/Keno - Revision history

Max: /* Idea */

2020-04-28T09:42:11Z

Idea

← Older revision		Revision as of 09:42, 28 April 2020
Line 4:		Line 4:

	=== Idea ===		=== Idea ===
			In the 1980s, British [https://www.channel4.com Channel 4] tried to imagine the TV of the future. They created Max Headroom as the host of a music show. He was supposed to be an AI character although played by an actual human actor, [[wikipedia:Matt Frewer\|Matt Frewer]]. After shooting, the fragments were cut in a way that would be called “[https://www.pbs.org/video/off-book-art-glitch glitchy]” nowadays. This imperfection is a very important part of the character, serving as a signifier for an artificial humanoid character.
	In the 1980s, British [https://www.channel4.com/ Channel 4] tried to imagine the TV of the future. They created Max Headroom as the host of a music show. He was supposed to be an AI character although played by an actual human actor, [~~https~~:~~//en.wikipedia.org/wiki/Matt_Frewer~~ Matt Frewer]. After shooting, the fragments were cut in a way that would be called “[https://www.pbs.org/video/off-book-art-glitch/ glitchy]” nowadays. This imperfection is a very important part of the character, serving as a signifier for an artificial humanoid character.

	{{#ev:youtube\|vS17G1MXzLk}}		{{#ev:youtube\|vS17G1MXzLk}}

	When so called neural networks came up, a discussion ~~starte~~ about which kinds of ~~labor~~ can be done by so called artificial intelligence. Some people are convinced even artists and musicians will be replaced by computer systems.		When so called neural networks came up, a discussion started about which kinds of labour can be done by so called artificial intelligence. Some people are convinced even artists and musicians will be replaced by computer systems.
	[~~https~~:~~//en.wikipedia.org/wiki/Hatsune_Miku~~ Hatsune Miku] was originally the name voicebank which can be used with Yamaha’s Vocaloid software. From 2010 on, albums for Hatsune Miku have been produced. In 2012 “she” gave her first concert as a holograph, gaining huge popularity.		[[wikipedia:Hatsune Miku\|Hatsune Miku]] was originally the name voicebank which can be used with Yamaha’s Vocaloid software. From 2010 on, albums for Hatsune Miku have been produced. In 2012 “she” gave her first concert as a holograph, gaining huge popularity.

	{{#ev:youtube\|YSyWtESoeOc}}		{{#ev:youtube\|YSyWtESoeOc}}

Keno: /* Production */

2020-04-08T10:23:21Z

Production

← Older revision		Revision as of 10:23, 8 April 2020
Line 23:		Line 23:
	[[File:dog_01.gif]]		[[File:dog_01.gif]]

	[https://runwayml.com/ RunwayML] is a SaaS company providing shared machine learning models. For this experiment, the StyleGAN (to be more precise [https://github.com/NVlabs/stylegan2 StyleGAN2]) framework by NVIDIA was used, which gained popularity due to its ability of generating almost photorealistic faces. The model was trained with the [http://niessnerlab.org/projects/roessler2018faceforensics.html FaceForensics dataset] by Technische Universität München, consisting of videos of news hosts. Using [http://ffmpeg.org/ `ffmpeg`] a part of these video files were converted to image sequences and fed into RunwayML’s training system. After completing the training, a video was generated walking through different parameters for image generation, creating this fluid transition from one host to another.		[https://runwayml.com/ RunwayML] is a SaaS company providing shared machine learning models. For this experiment, the StyleGAN (to be more precise [https://github.com/NVlabs/stylegan2 StyleGAN2]) framework by NVIDIA was used, which gained popularity due to its ability of generating almost photorealistic faces. The model was trained with the [http://niessnerlab.org/projects/roessler2018faceforensics.html FaceForensics dataset] by Technische Universität München, consisting of videos of news hosts. Using [http://ffmpeg.org/ ffmpeg] a part of these video files were converted to image sequences and fed into RunwayML’s training system. After completing the training, a video was generated walking through different parameters for image generation, creating this fluid transition from one host to another.
	This training was completed after 2000 steps. The model can be expanded and the quality improved by continuing the training.		This training was completed after 2000 steps. The model can be expanded and the quality improved by continuing the training.

	[[File:runway.png]]		[[File:runway.png]]

Keno: /* Idea */ formatting

2020-04-08T10:17:04Z

Idea: formatting

← Older revision		Revision as of 10:17, 8 April 2020
Line 5:		Line 5:
	=== Idea ===		=== Idea ===

	In the 1980s, British [https://www.channel4.com/ Channel 4] tried to imagine the TV of the future. They created Max Headroom as the host of a music show. He was supposed to be an AI character although played by an actual human actor, [~~Matt Frewer~~ https://en.wikipedia.org/wiki/Matt_Frewer]. After shooting, the fragments were cut in a way that would be called “[https://www.pbs.org/video/off-book-art-glitch/ glitchy]” nowadays. This imperfection is a very important part of the character, serving as a signifier for an artificial humanoid character.		In the 1980s, British [https://www.channel4.com/ Channel 4] tried to imagine the TV of the future. They created Max Headroom as the host of a music show. He was supposed to be an AI character although played by an actual human actor, [https://en.wikipedia.org/wiki/Matt_Frewer Matt Frewer]. After shooting, the fragments were cut in a way that would be called “[https://www.pbs.org/video/off-book-art-glitch/ glitchy]” nowadays. This imperfection is a very important part of the character, serving as a signifier for an artificial humanoid character.

	{{#ev:youtube\|vS17G1MXzLk}}		{{#ev:youtube\|vS17G1MXzLk}}

Keno: /* News Anchors of the Future */

2020-04-08T10:16:23Z

News Anchors of the Future

← Older revision		Revision as of 10:16, 8 April 2020
Line 1:		Line 1:
	= News Anchors of the Future =		== News Anchors of the Future ==

	{{#ev:vimeo\|404982095}}		{{#ev:vimeo\|404982095}}

	== Idea ==		=== Idea ===

	In the 1980s, British [https://www.channel4.com/ Channel 4] tried to imagine the TV of the future. They created Max Headroom as the host of a music show. He was supposed to be an AI character although played by an actual human actor, [Matt Frewer https://en.wikipedia.org/wiki/Matt_Frewer]. After shooting, the fragments were cut in a way that would be called “[https://www.pbs.org/video/off-book-art-glitch/ glitchy]” nowadays. This imperfection is a very important part of the character, serving as a signifier for an artificial humanoid character.		In the 1980s, British [https://www.channel4.com/ Channel 4] tried to imagine the TV of the future. They created Max Headroom as the host of a music show. He was supposed to be an AI character although played by an actual human actor, [Matt Frewer https://en.wikipedia.org/wiki/Matt_Frewer]. After shooting, the fragments were cut in a way that would be called “[https://www.pbs.org/video/off-book-art-glitch/ glitchy]” nowadays. This imperfection is a very important part of the character, serving as a signifier for an artificial humanoid character.
Line 17:		Line 17:
	With this history in mind, how would avatars for TV news look like? Having trained a machine learning model with news host images, the software can generate new news hosts. Most approaches aim at generating a photorealistic representation of a human. Referring to Max Headroom, it is more interesting to create avatars looking human-like, having some flaws, and thus, to include technical characteristics in the design process.		With this history in mind, how would avatars for TV news look like? Having trained a machine learning model with news host images, the software can generate new news hosts. Most approaches aim at generating a photorealistic representation of a human. Referring to Max Headroom, it is more interesting to create avatars looking human-like, having some flaws, and thus, to include technical characteristics in the design process.

	== Production ==		=== Production ===

	First tests were carried out with the [https://github.com/NVlabs/few-shot-vid2vid few-show-vid2vid] framework by NVIDIA. At this time, the idea was different: The news host were supposed to have dog faces. Due to technical problems this approach was abandoned for now.		First tests were carried out with the [https://github.com/NVlabs/few-shot-vid2vid few-show-vid2vid] framework by NVIDIA. At this time, the idea was different: The news host were supposed to have dog faces. Due to technical problems this approach was abandoned for now.

Keno at 10:15, 8 April 2020

2020-04-08T10:15:09Z

← Older revision		Revision as of 10:15, 8 April 2020
Line 26:		Line 26:
	This training was completed after 2000 steps. The model can be expanded and the quality improved by continuing the training.		This training was completed after 2000 steps. The model can be expanded and the quality improved by continuing the training.

	[File:runway.png]		[[File:runway.png]]

Keno: Added documentation

2020-04-08T10:14:46Z

Added documentation

← Older revision		Revision as of 10:14, 8 April 2020
Line 1:		Line 1:
			= News Anchors of the Future =

	{{#ev:vimeo\|404982095}}		{{#ev:vimeo\|404982095}}

			== Idea ==

			In the 1980s, British [https://www.channel4.com/ Channel 4] tried to imagine the TV of the future. They created Max Headroom as the host of a music show. He was supposed to be an AI character although played by an actual human actor, [Matt Frewer https://en.wikipedia.org/wiki/Matt_Frewer]. After shooting, the fragments were cut in a way that would be called “[https://www.pbs.org/video/off-book-art-glitch/ glitchy]” nowadays. This imperfection is a very important part of the character, serving as a signifier for an artificial humanoid character.

			{{#ev:youtube\|vS17G1MXzLk}}

			When so called neural networks came up, a discussion starte about which kinds of labor can be done by so called artificial intelligence. Some people are convinced even artists and musicians will be replaced by computer systems.
			[https://en.wikipedia.org/wiki/Hatsune_Miku Hatsune Miku] was originally the name voicebank which can be used with Yamaha’s Vocaloid software. From 2010 on, albums for Hatsune Miku have been produced. In 2012 “she” gave her first concert as a holograph, gaining huge popularity.

			{{#ev:youtube\|YSyWtESoeOc}}

			Max Headroom and Hatsune Miku are popular examples for avatars, fictional characters with a virtual representation created through CGI and video cutting techniques.
			With this history in mind, how would avatars for TV news look like? Having trained a machine learning model with news host images, the software can generate new news hosts. Most approaches aim at generating a photorealistic representation of a human. Referring to Max Headroom, it is more interesting to create avatars looking human-like, having some flaws, and thus, to include technical characteristics in the design process.

			== Production ==

			First tests were carried out with the [https://github.com/NVlabs/few-shot-vid2vid few-show-vid2vid] framework by NVIDIA. At this time, the idea was different: The news host were supposed to have dog faces. Due to technical problems this approach was abandoned for now.

	[[File:dog_01.gif]]		[[File:dog_01.gif]]

			[https://runwayml.com/ RunwayML] is a SaaS company providing shared machine learning models. For this experiment, the StyleGAN (to be more precise [https://github.com/NVlabs/stylegan2 StyleGAN2]) framework by NVIDIA was used, which gained popularity due to its ability of generating almost photorealistic faces. The model was trained with the [http://niessnerlab.org/projects/roessler2018faceforensics.html FaceForensics dataset] by Technische Universität München, consisting of videos of news hosts. Using [http://ffmpeg.org/ `ffmpeg`] a part of these video files were converted to image sequences and fed into RunwayML’s training system. After completing the training, a video was generated walking through different parameters for image generation, creating this fluid transition from one host to another.
			This training was completed after 2000 steps. The model can be expanded and the quality improved by continuing the training.

			[File:runway.png]

Keno: Added result video

2020-04-07T14:00:37Z

Added result video

← Older revision		Revision as of 14:00, 7 April 2020
Line 1:		Line 1:
			{{#ev:vimeo\|404982095}}

	[[File:dog_01.gif]]		[[File:dog_01.gif]]

Keno at 10:25, 30 March 2020

2020-03-30T10:25:07Z

← Older revision		Revision as of 10:25, 30 March 2020
Line 1:		Line 1:
	[File:dog_01.gif]		[[File:dog_01.gif]]

Keno at 10:24, 30 March 2020

2020-03-30T10:24:56Z

← Older revision		Revision as of 10:24, 30 March 2020
Line 1:		Line 1:
	[[File:dog_01.gif]]		[File:dog_01.gif]

Keno: Created page with "File:dog_01.gif"

2020-03-30T10:19:53Z

Created page with "File:dog_01.gif"

New page

[[File:dog_01.gif]]