Virtual Human: A Comprehensive Survey on Academic and Applications

Abstract

As a creative method for virtual human individuals based on multiple fusion technologies such as artificial intelligence, computer graphics, and speech synthesis, virtual human technology has developed rapidly since its birth, and continuous discussions and studies have been conducted in both academia and industry. Starting from the film and television industries, the cross-disciplinary application of virtual human has been continuously recognized and applied in fields such as media, games, and finance. Although virtual human has achieved sufficient development and innovation, it faces many challenges such as emotion recognition, privacy, and security, as well as the uncanny valley effect. This article starts with the development history of virtual human and analyzes the current academic research status and application scenarios in combination with the characteristics, technical architecture, and application of virtual human technology. At the same time, this article sorts out seven mainstream application scenarios of virtual human and analyzes their main advantages and possible future challenges. This article provides a valuable reference for subsequent related research by exploring development trends, application fields, and future research trends in virtual human.

Blockchain-Based Decentralised Privacy-Preserving Machine Learning Authentication and Verification With Immersive Devices in the Urban Metaverse Ecosystem

“…UMaaS-3 Virtual human systems, i) by achieving both realistic virtual humans with face expression recognition and smooth and flexible dialogue engines with chatbots, and ii) by targeting to achieve emotional recognition and emotional empathy, typically consist of five main modules: character generation, voice generation, animation generation, audio and video synthesis display, and interaction using information technologies, such as computer graphics, motion capture, ML, high-precision rendering, and speech synthesis [67]. Convincing, false representations of individuals -by exploiting the immersive nature of the metaverse -can be created, as fake avatars using high-level imitation technologies (e.g.…”

PIXGAN-Drone: 3D Avatar of Human Body Reconstruction From Multi-View 2D Images

“…3D human avatar reconstruction methods from 2D images have achieved a significant role in computer vision and interactive virtual graphic environments, as well as being the focus of attention in the animation industry community [1]. Recently, deep adversarial approaches have often been used for 3D models of human body reconstruction from 2D images.…”