Digital humans are human-like characters populating digital worlds. They are already key aspects of the rapidly evolving areas of extended reality, virtual production and gaming. Extending beyond the entertainment world, they are becoming more and more commonplace in retail, sports, social media, education, health and many other fields. There is thus a need to automatically populate these applications with digital humans, but automatically created characters are still uncanny. There are many scientific and technical challenges to make them realistic.
Realistic representation of digital humans is now possible with the capture of high-quality data and appropriate rendering techniques. While capturing of accurate and relightable data is required to produce assets for realistic characters, motion capture data is also needed to synthesize lifelike animation, as well as data related to the internal body parts (muscles, skeleton, etc.). Besides, the real-time rendering of photorealistic humans is not perfect yet, and
does not overcome the uncanny valley. Finally, behavior models for digital humans are required to make them authentic and interactive. New deep learning techniques have recently opened the way to such models that would enable seamless communication between digital and real humans.
Therefore, the study of digital humans encompasses many fields of study such as data capture, rendering, animation, interaction, or deep learning. The aim of this Research Topic in Frontiers in Virtual Reality is to provide a common ground to share knowledge among experts in these fields. It would cover research works providing a new step toward the creation of lifelike digital humans.
Topics of interest include, but are not limited to:
- Capture systems (photogrametry, ligthing, motion, etc)
- Creation of Digital Humans (modeling, synthesis)
- Real-time Rendering of Digital Humans
- Extended reality experiences with Digital Humans (VR AR, MR)
Keywords: Virtual Reality, Digital Human, Capture, Characters, Animation, Render, Deep Learning