//
With the rise of AIGC content, multimodal media models have gradually entered everyone's field of vision, and the development of LLM has given people new thinking about future audio and video tools. On July 29th, LiveVideoStackCon2023 Shanghai Station AIGC and content production session will gather the most popular AIGC topics and share them with you.
AIGC and content production
Driven by technology, demand, and the industrial chain, people have also entered the emerging content production era of AIGC after UGC and PGC. But AIGC is not a single technology. Its essence is a high-degree-of-freedom and low-threshold content production capability formed by using AI empowerment technology, and this capability will serve creators and creators in various scenarios. producer.
TOPIC1 "Huawei Cloud MetaStudio multi-modal digital human progress and challenges introduction"
Li Minglei, Head of Virtual Digital Human Technology, Huawei
As a master of AI capabilities, digital humans involve technologies such as computer vision, computer graphics, speech processing, and natural language processing, and are being used more and more in fields such as finance, government affairs, media, and e-commerce. This report mainly introduces the main progress of HUAWEI CLOUD in the field of digital human, including 2D digital human driving, 3D digital human modeling, binding, driving, and emotional digital human generation. It also introduces some challenges in the field of digital human.
This sharing will be divided into three parts. The first part introduces the introduction of HUAWEI CLOUD cloud-native digital human production pipeline and business planning; the second part introduces the progress of HUAWEI CLOUD 2D digital human technology, how to solve lip-drive, body arrangement, mobile Scene driving and other issues; the third part introduces the progress of HUAWEI CLOUD 3D digital human modeling, binding, driving and other technologies.
TOPIC2 "Analysis of AIGC audio and video tools and thinking about future innovation opportunities"
Wang Wenyu-PPIO CTO&Co-Founder
What changes will the large language model LLM and other AIGC technology developments bring to the audio and video industry? I will take stock of some very good AIGC applications that are popular in Silicon Valley, and then think about technology + business, and analyze the opportunities for innovation and entrepreneurship in the future of audio and video combined with AIGC.
Speech Outline:
1. AIGC has brought tenfold changes to the entire industry; 2. Take stock of several AIGC applications in Silicon Valley;
3. Think about the nature of AIGC and the connection of audio and video; 4. Where are the future opportunities for innovation and entrepreneurship in the audio and video industry
TOPIC3 "AI Redefines the "New Paradigm" of Audio and Video Productivity"
Wu Lei-Vice President of Wangxin Technology
Main framework: 1. Facing the new era of Moore's Law, the impact of AI technology on audio and video content; 2. AI's innovation in audio and video productivity, what kind of infrastructure and computing power platform do you need to build? 3. AI intelligent application and construction practice.
TOPIC4 "From AIGC to Multimodal Media Model"
Song Li-Professor of Shanghai Jiaotong University
This speech will demonstrate the characteristics of the new generation of multimodal media and the new trend of intelligent cross-modal coding based on large models in the three aspects of multimodal media generation, multimodal media coding and multimodal media interaction.
▲Scan the QR code in the picture or click " Read the original text " ▲
Check out more exciting topics of LiveVideoStackCon 2023 Shanghai Station