The salesperson hawking Brother printers on Taobao works hard--like, really hard. At any time of the day, even when there's no audience on the Chinese ecommerce platform, the same woman wearing a white shirt and black skirt is always livestreaming, boasting about the various features of different office printers. She has a phone in one hand and often checks it as if to read a sales script or monitor the viewer comments coming in. "My friends, I've gotta plug this game-changing office tool that can double your workplace efficiency, " the salesperson said during one recent broadcast, trying to achieve the delicate balance between friendliness and precision that has come to define the billion-dollar livestream ecommerce industry in China. Occasionally, she greeted the invisible audience.

Understanding the world in first-person view is fundamental in Augmented Reality (AR). This immersive perspective brings dramatic visual changes and unique challenges compared to third-person views. Synthetic data has empowered third-person-view vision models, but its application to embodied egocentric perception tasks remains largely unexplored. A critical challenge lies in simulating natural human movements and behaviors that effectively steer the embodied cameras to capture a faithful egocentric representation of the 3D world. To address this challenge, we introduce EgoGen, a new synthetic data generator that can produce accurate and rich ground-truth training data for egocentric perception tasks. At the heart of EgoGen is a novel human motion synthesis model that directly leverages egocentric visual inputs of a virtual human to sense the 3D environment. Combined with collision-avoiding motion primitives and a two-stage reinforcement learning approach, our motion synthesis model offers a closed-loop solution where the embodied perception and movement of the virtual human are seamlessly coupled. Compared to previous works, our model eliminates the need for a pre-defined global path, and is directly applicable to dynamic environments. Combined with our easy-to-use and scalable data generation pipeline, we demonstrate EgoGen's efficacy in three tasks: mapping and localization for head-mounted cameras, egocentric camera tracking, and human mesh recovery from egocentric views. EgoGen will be fully open-sourced, offering a practical solution for creating realistic egocentric training data and aiming to serve as a useful tool for egocentric computer vision research. Refer to our project page: https://ego-gen.github.io/.

Digital humans could end up replacing supermodels as artificial intelligence is set to revolutionise the way we order clothes online. A German company has launched a system that sees state-of-the-art'digital humans' pose for campaigns. The digi-models, who come with names including Joy, Nina, Noah and Theo, can be customised and individualised to a brand's preference. A German company has launched a system that sees state-of-the-art'digital humans' pose for campaigns There is also the option for real models, such as Kate Moss or Kaia Gerber, to licence their likenesses. They can either be recreated completely digitally or have a scan done of their entire body.

Blockchain enables creators to package and monetize their digital content in new ways. However, it's not the only tech stack that is doing so. Artificial intelligence (AI) is also redefining creativity in the digital space, and here's how. DALL-E, Stable Diffusion, and Midjourney are all generative AI models. They use AI algorithms to automatically generate digital content based on a simple prompt that would otherwise take a human a long time to complete.

Prosody plays a vital role in verbal communication. Acoustic cues of prosody have been examined extensively. However, prosodic characteristics are not only perceived auditorily, but also visually based on head and facial movements. The purpose of this report is to present a method for examining audiovisual prosody using virtual reality. We show that animations based on a virtual human provide motion cues similar to those obtained from video recordings of a real talker. The use of virtual reality opens up new avenues for examining multimodal effects of verbal communication. We discuss the method in the framework of examining prosody perception in cochlear implant listeners.

Social media platforms are a huge part of everyone’s life today. Regarded as entertainment and used only in the free time a few years ago, today it is the most influential domain in the world when…

AI continues to transform every industry it touches, and broadcast media is no exception. Already available within Asia, broadcast news stations such as Arirang TV in Korea and CCTV in China use DeepBrain AI's Virtual Humans, known as AI Anchors, to augment the regular newsfeed with AI specials, breaking news, and hourly updates throughout the day. "I will just write up an article, and she (Virtual Human) can deliver it right away," stated Moon Connyoung, Principal News Anchor and Managing Editor at Arirang News. The video synthesis technology from DeepBrain AI has applications across many different industries, including media, banking, education, and customer service. "DeepBrain AI's solutions have already been deployed at banks, retail stores, and TV stations across Asia. I am excited to bring our technology to the US and the 2022 NAB Show," stated Eric Jang, CEO of DeepBrain AI.

Krafton, the creator of PUBG, one of the most popular battle royale games globally, has plans to create new artificial intelligence-powered synthetic beings. This is the company's first foray into the realm of the metaverse. Krafton is set on creating realistic virtual avatars for usage in games, eSports, and as virtual influencers and singers. In addition, to strengthen their communication abilities, Krafton plans to use hyperrealism character manufacturing technology to build digital avatars of humans using artificial intelligence (AI), text-to-speech, speech-to-text, and voice-to-face. Krafton CEO CH Kim said last month at a town hall meeting that the business will actively harness new technology to provide unique experiences to gamers and creators.

'Rozy' is a virtual human that was created Sidus Studio X last year in August. According to CEO Baek Seung Yeop, Rozy currently has advertising contracts with companies and a significant amount of sponsorships. As CEO Baek said, the reason for the popularity of virtual humans is that there is no fear that advertisements will be suspended due to unsavory privacy scandals after the AI model is selected as the advertising model. The location and scene can be created through computer graphics, so the virtual model is not limited in time and space, and unlike real people. The other advantage is that period in which the model can be active is very long or eternal because the virtual human doesn't get sick or grow old.

With the advancement of technology, AI influencers and virtual human models are becoming the new trend. It has recently emerged as a blue-chip in the advertising industry because there are no privacy scandals and there are no time-space restrictions with these virtual humans. In particular, the use of virtual humans seems to be gaining more momentum in the COVID-19 pandemic, where there are many restrictions on travel and limitations on the number of people gathering. On September 10, Baek Seung Yeop, CEO of Sidus Studio X that created'Rozy,' the newly rising blue-chip in the advertisement industry, explained, "These days, celebrities are sometimes withdrawn from dramas that they have been filming because of school violence scandals or bullying controversies. However, virtual humans have zero scandals to worry about."