Learning Human Body Shapes in Motion
Accurately representing and animating the human body in 3D is critical for games, special effects and virtual reality. Previously, this required extensive hand animation. Today realistic 3D avatars can be learned from thousands of 3D scans. This course takes participants through the process of learning and using a high quality 3D model of the human body.
The 3D representation of human form has been central to human art for 40,000 years. While the first 3D bodies were carved from mammoth tusk, the present and future require 3D shapes that look and move realistically. Currently, representing body shape with high realism requires expert hand modeling and animation. The advent of 3D scanning creates the opportunity to learn realistic models of body shape and how it deforms with motion.
Scanning, however, is just the beginning. Building a model requires putting scans into accurate correspondence, choosing a representation for shape, and optimizing the model to fit training data. Consequently this course presents a “how to” tutorial covering these key topics:
- data capture
- mesh alignment
- choice of shape representation
- dealing with varying body shape
- modeling articulation
- capturing and modeling soft-tissue motions
- fitting models to data
- applications in VR, animation, fashion, and psychology
Attendees will walk away with a state-of-the art 3D body model that they can readily use for their own research purposes. The course includes a hands-on section in which participants can create a body, edit its shape, and animate it in motion.
Who is it for?
The course is designed for computer graphics students and researchers. It does not assume strong graphics experience and will introduce the main methods and models in the field. The course is ideal for anyone who needs a 3D body model for animation, pose estimation, training, etc.
Instructors
The tutorial is taught by a team from the Max Planck Institute for Intelligent Systems, who have spent years developing 3D human body models for vision, graphics and learning. In particular the course will cover topics from recent SIGGRAPH and SIGGRAPH Asia papers in an integrated and accessible way.