ETRI Develops Hyper-Realistic AI Avatars from Single Photo for Enhanced Human-Machine Interaction
2 Sources
2 Sources
[1]
Hyper-realistic AI technology creates avatars from a single photo
Electronics and Telecommunications Research Institute (ETRI) has developed hyper-realistic AI technology that can create an avatar that speaks naturally like a real person using only a single portrait photo. The technology is being seen as a next-generation interface that enables intuitive interaction between vehicles and humans in preparation for the era of fully autonomous driving, and is expected to spread across the digital human industry. While traditional current speech-driven AI assistants in office environments or navigation systems in vehicles are limited to simply carrying out commands, ETRI's hyper-realistic AI avatars have sophisticated facial expressions and mouth movements that enable natural, human-like conversations. This allows for a more human-centered human-machine interaction, such as an in-vehicle AI driver talking to the driver or interacting with pedestrians. The core of this technology is a unique algorithm that, unlike traditional generative AI, selectively learns and synthesizes parts of the face that are directly related to utterance, such as the lips and chin. This approach reduces unnecessary information learning and allows for more sophisticated facial expressions, including mouth shapes, teeth, and skin wrinkles. ETRI explained that the technology has demonstrated superior performance in terms of synthetic visual quality and lip synchronization accuracy as presented at major international conferences such as CVPR and AAAI. In addition to autonomous vehicles, this technology can be utilized in various industries such as kiosks, bank counters, news presentations, advertising models, and is expected to drive innovation in the AI-based digital human industry. ETRI's Mobility User Experience Research Section is currently focusing on human-machine interaction (HMI) technologies, and is also developing AI-based driver interface technologies that analyze driver and pedestrian emotions, fatigue, concentration, etc. Daesub Yoon, Director of the Mobility User Experience Research Section, said, "As mobility technology becomes more advanced, the elderly and socially disadvantaged may be marginalized. We hope that this AI avatar technology will contribute to improving digital literacy and make smart mobility services more accessible to all." And Senior Researcher Daewoong Choi also said, "We plan to further advance our generative AI technology so that AI avatars can naturally talk and move like real people. In the future, we're aiming for interactions that can replace some human labor for ordering, consulting, and more." The technology is currently registered on the ETRI Technology Transfer site as "A Framework for Photorealistic Talking Face Generation." The researchers will also actively pursue technology transfer and strategies for commercialization in various industries.
[2]
ETRI Creates Hyper-Realistic AI Avatars from a Single Photo | Newswise
Newswise -- Electronics and Telecommunications Research Institute (ETRI) has developed hyper-realistic AI technology that can create an avatar that speaks naturally like a real person using only a single portrait photo. The technology is being seen as a next-generation interface that enables intuitive interaction between vehicles and humans in preparation for the era of fully autonomous driving, and is expected to spread across the digital human industry. While traditional current speech-driven AI assistants in office environments or navigation systems in vehicles are limited to simply carrying out commands, ETRI's hyper-realistic AI avatars have sophisticated facial expressions and mouth movements that enable natural, human-like conversations. This allows for a more human-centered human-machine interaction, such as an in-vehicle AI driver talking to the driver or interacting with pedestrians. The core of this technology is a unique algorithm that, unlike traditional generative AI, selectively learns and synthesizes parts of the face that are directly related to utterance, such as the lips and chin. This approach reduces unnecessary information learning and allows for more sophisticated facial expressions, including mouth shapes, teeth, and skin wrinkles. ETRI explained that the technology has demonstrated superior performance in terms of synthetic visual quality and lip synchronization accuracy as presented at major international conferences such as CVPR and AAAI. In addition to autonomous vehicles, this technology can be utilized in various industries such as â–²kiosks, â–²bank counters, â–²news presentations, â–²advertising models, and is expected to drive innovation in the AI-based digital human industry. ETRI's Mobility User Experience Research Section is currently focusing on human-machine interaction (HMI) technologies, and is also developing AI-based driver interface technologies that analyze driver and pedestrian emotions, fatigue, concentration, etc. Daesub Yoon, Director of the Mobility User Experience Research Section, said, "As mobility technology becomes more advanced, the elderly and socially disadvantaged may be marginalized. We hope that this AI avatar technology will contribute to improving digital literacy and make smart mobility services more accessible to all." And Senior Researcher Daewoong Choi also said, "We plan to further advance our generative AI technology so that AI avatars can naturally talk and move like real people. In the future, we're aiming for interactions that can replace some human labor for ordering, consulting, and more." The technology is currently registered on the ETRI Technology Transfer site as 'A Framework for Photorealistic Talking Face Generation'. The researchers will also actively pursue technology transfer and strategies for commercialization in various industries. ### The research was conducted as part of the 'Next Generation Leading New Research Project' conducted by Electronics and Telecommunications Research Institute (ETRI) through the task 'Development of fundamental technology for controllable photo-realistic video generation AI.'
Share
Share
Copy Link
Electronics and Telecommunications Research Institute (ETRI) has created AI technology that generates lifelike avatars from a single portrait, potentially revolutionizing human-machine interfaces in autonomous vehicles and various industries.
Breakthrough in AI Avatar Technology
The Electronics and Telecommunications Research Institute (ETRI) has made a significant advancement in artificial intelligence by developing hyper-realistic AI technology capable of creating lifelike avatars from a single portrait photo. This innovation is poised to revolutionize human-machine interactions, particularly in the realm of autonomous vehicles and beyond
1
2
.Enhanced Human-Machine Interaction
Unlike traditional AI assistants that merely execute commands, ETRI's hyper-realistic avatars boast sophisticated facial expressions and mouth movements, enabling natural, human-like conversations. This technology represents a leap forward in creating more intuitive and engaging interfaces between humans and machines
1
2
.
Source: Tech Xplore
The potential applications are vast, ranging from in-vehicle AI drivers communicating with human passengers to AI avatars interacting with pedestrians. This human-centered approach to AI interaction is expected to make smart mobility services more accessible and user-friendly
1
2
.Innovative Algorithm and Superior Performance
At the heart of this technology lies a unique algorithm that sets it apart from traditional generative AI. The system selectively learns and synthesizes facial features directly related to speech, such as lips and chin movements. This targeted approach reduces unnecessary information processing and allows for more nuanced facial expressions, including realistic mouth shapes, teeth visibility, and skin wrinkles
1
2
.ETRI reports that their technology has demonstrated superior performance in terms of synthetic visual quality and lip synchronization accuracy. These achievements have been recognized at major international conferences such as CVPR and AAAI
1
2
.Wide-Ranging Applications and Industry Impact
While the technology's primary focus is on enhancing human-machine interaction in autonomous vehicles, its potential extends far beyond. ETRI envisions applications in various sectors, including:
- Interactive kiosks
- Bank customer service
- News presentations
- Advertising and modeling
- General AI-based digital human industry
1
2
The Mobility User Experience Research Section at ETRI is also developing complementary AI-based driver interface technologies that can analyze emotions, fatigue, and concentration levels of both drivers and pedestrians
1
2
.Related Stories
Addressing Social Concerns and Future Developments
Daesub Yoon, Director of the Mobility User Experience Research Section, emphasized the technology's potential to bridge digital divides: "As mobility technology becomes more advanced, the elderly and socially disadvantaged may be marginalized. We hope that this AI avatar technology will contribute to improving digital literacy and make smart mobility services more accessible to all"
1
2
.Senior Researcher Daewoong Choi outlined future aspirations for the technology: "We plan to further advance our generative AI technology so that AI avatars can naturally talk and move like real people. In the future, we're aiming for interactions that can replace some human labor for ordering, consulting, and more"
1
2
.Commercialization and Technology Transfer
The technology, currently registered as "A Framework for Photorealistic Talking Face Generation" on the ETRI Technology Transfer site, is poised for commercialization. ETRI researchers are actively pursuing technology transfer and strategies to implement this innovation across various industries
1
2
.References
Summarized by
Navi
Related Stories
Weekly Highlights
Weekly Highlights
Today's Top Stories
Your Daily Dose of Curated AI News
Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Spend less time searching for the latest in AI and get straight to action.
