Virtual Humans

Abstract

Human digitalization is required in many applications, such as AR/VR, robotics, games, and social networking. The course covers core techniques and fundamental tools necessary for perceiving and modeling humans. The main topics include human body modeling, human appearance and motion modeling, and human-​scene interaction capture and modeling.

Objectives

After attending this course, students will be able to implement basic systems to estimate human pose, shape, and motion from videos; furthermore, students will be able to create basic human avatars from various visual inputs.

Content

We will focus on all aspects of 3D human capture, modelling, and synthesis, including
⁃ Basic concept of 3D representations
⁃ Human body models;
⁃ Human motion capture;
⁃ Non-​rigid surface tracking and reconstruction;
⁃ Neural rendering

Lecture Notes

Slides

Literature

Computer Vision: Algorithms and applications by Richard Szeliski.
Deep Learning: by Goodfellow, Bengio, and Courville

Prerequisites

This is an advanced lecture for learning to model and synthesize 3D humans. We assume you have basic knowledge of computer vision, deep learning, and computer graphics; a solid understanding of linear algebra, probability, and calculus.
The following courses are highly recommended as a prerequisite
visual computing, computer vision, and deep learning.

Administration

Schedule