Use technology to create a popular "virtual human" - Apsara 2022

Date: Oct 1, 2022

Recently, AYAYI, the first hyper-realistic digital person Apsara conference 2022 in China, announced to join Alibaba as the digital manager of Tmall Super Brand Day. The two will jointly open up the marketing world of the Metaverse. In the future, she will unlock multiple identities with Tmall, such as NFT artist, digital curator, fashion brand manager, top-notch digital person, etc, Apsara conference 2022.

When it comes to virtual digital people, the first thing that comes to mind is Luo Tianyi, who was born in 2012. Her appearance fills the blank virtual idol market in China. Although she only had a voice and a portrait at first, over the past nine years, fans have continued to write songs, draw illustrations, and make MMD for her. These fan creations filled the initial blank little by little. Compared with real idols, virtual idols that grow up relying on UGC content are more like a pure cultivation-style star-making. Apsara conference 2022, virtual idols with dimension characteristics represented by Luo Tianyi began to shine in the Spring Festival Gala, which means that the respect and recognition of dimension culture by national platforms is also a beneficial interaction between virtual and reality Apsara conference 2022.

According to data from iMedia Research, the scale of China's virtual idol core industry in 2020 is 3.46 billion yuan, a year-on-year increase of 70.3%, and it is expected to reach 6.22 billion yuan in 2021; on the other hand, with the continuous exploration of commercial value, the more More and more industries are linked with virtual idols. The scale of the industry driven by virtual idols will be 64.56 billion yuan in 2020 and is expected to be 107.49 billion yuan in Apsara conference 2022.

On foreign short video platforms, virtual digital people are also very popular. A virtual idol named Lil Miquela, who is a 19-year-old mixed-race girl with cute freckles, has long lived in Los Angeles, and has virtual models and musicians of Hispanic, Brazilian and American descent. Apsara conference 2022 according to a report by CCTV on January 30, 2021, Lil Miquela's income in 2019 is about 76 million yuan.

What is a virtual digital human?

The term "virtual digital human" originated from the "Visible Human Project" (YHP) initiated by the US National Library of Medicine in 1989. In 2001, the concept of "digital virtual human body" was proposed in the 174th academic symposium of the Xiangshan Science Conference with the theme of "China's digital virtual human body". These "virtual digital people" mainly refer to the visualization of human body structure, showing the size, shape, position and mutual spatial relationship between organs of human anatomical structure in three-dimensional form, that is, using human body information to realize the digitization of human anatomical structure. It is mainly used in human anatomy teaching and clinical diagnosis and treatment in the medical field Apsara conference 2022.

Different from the above-mentioned digital human body in the medical field, the virtual digital human (hereinafter referred to as "digital human") currently discussed around the metaverse on the Internet refers to a virtual human with a digital appearance. Unlike physical robots, virtual digital humans rely on display devices to exist. Apsara conference 2022 virtual digital human should have the following three characteristics: First, it has the appearance of a person, with specific characteristics such as appearance, gender and personality; second, it has the behavior of a person, and it has the ability to express with language, facial expressions and body movements; third It is the ability to have a human mind, to recognize the external environment, and to communicate and interact with people.

In recent years, thanks to the breakthrough of deep learning algorithms, the production process of digital human has become simpler, and virtual digital human has begun to enter the public's field of vision and be applied in all walks of life. For example, entertainment digital human (such as virtual anchor, virtual idol), educational digital human (such as virtual teacher), assistant digital human (such as virtual customer service, virtual tour guide, intelligent assistant), film and television digital human (such as stuntman or virtual actor), etc. Virtual digital humans with different shapes and functions empower film and television, media, games, finance, cultural tourism and other fields, and provide users with customized services according to their needs Apsara conference 2022.

Apsara conference 2022 terms of implementation technology, the virtual digital human system is generally composed of five modules: character image, voice generation, animation generation, audio and video synthesis display, and interaction. Among them, the most basic is the character image technology. According to the dimension of character graphics resources, it can be divided into two categories: 2D and 3D. From the appearance, it can be divided into cartoon, anthropomorphic, realistic, hyper-realistic and other styles.

Alibaba Cloud Cartoon Wisdom: Create a virtual idol around you

Because there are certain technical thresholds in the construction of virtual human characters, for ordinary people, virtual human seems to be still in the idol stage and can only be viewed from a distance. However, the team from Alibaba Cloud Video Cloud, through optimized algorithm technology, allows ordinary people to have the opportunity to create their own cartoon images and create "civilian idols" in the virtual world. In the developer exhibition area of ​​the Apsara conference 2022, Alibaba Cloud demonstrated the latest technology - the cartoon smart painting project, which attracted nearly 2,000 experiencers and became a hit at the Apsara conference 2022. This technology adopts the face stylization technical scheme of hidden variable mapping. Through the machine learning algorithm, the original facial features of the photographer and the target training style can be deeply integrated to reconstruct the shape of the face, which not only conforms to the user's facial features, but also With cartoon stylization, it can also track the user's facial posture and rich expressions to generate real-time animation.