Abstract

This course covers the core technologies required to model and simulate digital humans. The curriculum includes human body modeling, human motion capture, data-driven human motion synthesis, and ML-based generative models. Each topic will be extensively illustrated with examples to provide a comprehensive understanding of the subject matter. 

 

Objectives

Students will learn how to estimate human pose, shape, and motion from videos and create basic human avatars from various visual inputs. Students will also learn how to represent and algorithmically generate motions for digital characters. To help students prepare for the midterm exam, four ungraded exercises will be released following the corresponding lectures and will be reviewed during the tutorial sessions.

 

Content

- Basic concepts of 3D representations
- Human body/hand models
- Human motion capture
- Neural rendering
- Transformers
- Generative models for digital humans

 

Lecture Notes

Lecture and tutorial slides will be available on moodle.

 

Prerequisites

Experience with python and C++ programming, numerical linear algebra, multivariate calculus and probability theory. Some background in deep learning, computer vision, physics-based modeling, kinematics, and dynamics is preferred.

 

Administration

Number263-​5806-00L
LecturerProf. Dr. Siyu Tang, Dr. Sergey Prokudin
Assistants

Kaifeng Zhao (head TA)

Korrawe Karunratanakul

Marko Mihajlovic

Shaofei Wang

Gen Li

Location and Time

Lecture:

Tue    14:15-17:00   LFO C 13

Tutorial:

Thu    16:15-18:00   ETF E 1

Moodle

https://moodle-app2.let.ethz.ch/course/view.php?id=25021

ECTS Credits8
ExamThe grade will be determined by 40% interim examination and 60% final project presentation and report.

 

Schedule

Lecture

WeekDate (14pm-​17pm)Topic
0118-FebIntroduction
0225-FebHuman body models
034-MarFrom Images to Human Models
0411-MarMesh-based Human Avatars
0518-MarVolumetric Human Avatars (Neural Fields)
0625-MarPoint-based Human Avatars (3D Gaussian Splats)
071-AprGenerative Models
088-AprHuman motion
0915-AprMidterm Exam
1022-AprWeek after Easter: no classes
1129-AprProject presentation
126-MayProject Office Hour
1313-MayProject Office Hour
1420-MayProject Office Hour
1527-MayProject presentation

 

Tutorial 

WeekDate (16pm-​18pm)Topic
0120-Feb 
0227-Feb 
036-MarExercise 1
0413-MarPytorch Tutorial
0520-MarExercise 2
0627-MarExercise 3
073-AprProject Introduction
0810-AprExercise 4
0917-AprCluster Tutorial
1024-Apr
Week after Easter: no classes
111-MayProject Office Hour
128-MayProject Office Hour
1315-MayProject Office Hour
1422-MayProject Office Hour