Virtual Humans

Course: Winter Semester 2023

Continuous Learning of Multimodal Data Streams

University of Tuebingen

appearance hps

Description

A virtual human is a digital representation of a real human. Virtual humans (VH) should look, move and eventually think like real humans. Building such VH is one of the long standing goals of Artificial Intelligence. Learning them requires techniques and algorithms at the intersection of Machine Learning, Computer Vision and Computer Graphics. In this course, we will cover the key mathematical foundations and computational tools to learn VH from 3D scans, images and video of real humans. The course will cover classical representations of humans based on 3D meshes and textures, as well as modern ones where the appearance and behavior of virtual humans are encoded in neural networks.
The following topics will be covered in the course:
  • Body and Clothing models.
  • Rotations, surface paramterization etc.
  • Neural Implicits and NeRF based human models.
  • Human Behaviour capture and synthesis.

Organization

Course module number is ML4508. This course is worth 9 ECTS points. There will be one lecture and one tutorial session per week. The TAs and their office hours are:
  • Riccardo Marin (mail) [Wednesday, 16.30-17.30 (Maria-von-Linden Strasse 6, 2nd floor, 20-8/A14)]
  • Xianghui Xie (mail) [Friday, 16.00-17.00 (Maria-von-Linden Strasse 6, 2nd floor, 20-31/A12)]
  • Ilya Petrov (mail) [Thursday, 16.00-17.00 (Maria-von-Linden Strasse 6, 2nd floor, 20-7/A18)]

Prerequisites

Basic knowledge of linear algebra, probability theory, optimization, and programming skills in Python are required. Having experience with PyTorch, and knowledge of computer graphics concepts (geometry representation, rendering) is a plus.

Location


Assignments

There will be 3 bi-weekly assignments and a research project.

Exam

The final exams will take place on-site in Tuebingen, and you need to be physically present. There is going to be one exam at the beginning of the semester break and one at the end of the semester break. The exam format will be determined by the number of students attending the course (written in case of many people attending or oral in case of smaller attendance). The format will be announced at the start of the course.
Tentative date for the exam: 26.02.2024, 10.00-12.00 at Lecture Hall (ground floor) Maria-von-Linden Strasse 6.


Schedule for Lectures

# Date & Time Location Title Links
01: Oct. 25, 800-1000 A301, Sand 1 Organization and Introduction to Body Models YouTube | pdf 1 2 3 | pptx 1 2 3
02: Nov. 08, 800-1000 Lect. Hall, MvL 6 Image formations and Rotations YouTube | pdf 1 2 | pptx 1 2
03: Nov. 15, 800-1000 A301, Sand 1 Surface Representations and Procrustes alignment YouTube | pdf 1 2 | pptx 1 2
04: Nov. 22, 800-1000 Lect. Hall, MvL 6 ICP, Non rigid alignment & vertex based models YouTube | pdf 1 2 | pptx 1 2
05: Nov. 29, 800-1000 Lect. Hall, MvL 6 Fitting SMPL to scans YouTube | pdf 1 2 | pptx 1 2
06: Dec. 06, 800-1000 Lect. Hall, MvL 6 Fitting SMPL to images YouTube | pdf 1 2 | pptx 1 2
07: Dec. 13, 800-1000 Lect. Hall, MvL 6 Fitting SMPL to IMUs YouTube | pdf 1 2 | pptx 1 2
08: Dec. 18, 1600-1800 Lect. Hall, MvL 6 Vertex based Clothing Models YouTube | pdf 1 | pptx 1
09: Dec. 20, 800-1000 Lect. Hall, MvL 6 Neural Implicits and Point based Clothing Models YouTube | pdf 1 | pptx 1
10: Jan. 10, 800-1000 Lect. Hall, MvL 6 Humans and NeRFs YouTube | pdf 1 2 | pptx 1 1
11: Jan. 24, 800-1000 Lect. Hall, MvL 6 Human behaviour capture YouTube | pdf 1 2 | pptx 1 2
12: Jan. 31, 800-1000 Lect. Hall, MvL 6 Human behaviour synthesis YouTube | pdf 1 | pptx 1
13: Feb. 06, 900-1000 Lect. Hall, MvL 6 Human motion synthesis and mock exam | pdf 1 | pptx 1


Schedule for Tutorials

# Date & Time Location Title
01: Oct. 26, 1415-1600 Lect. Hall, MvL 6 Organization and Introduction to Body Models
02: Nov. 09, 1415-1600 Lect. Hall, MvL 6 Image formations and Rotations
03: Nov. 16, 1415-1600 Lect. Hall, MvL 6 Surface Representations and Procrustes alignment
04: Nov. 23, 1415-1600 Lect. Hall, MvL 6 ICP, Non rigid alignment and vertex based body models
05: Nov. 30, 1415-1600 Lect. Hall, MvL 6 Fitting SMPL to scans
06: Dec. 07, 1415-1600 Lect. Hall, MvL 6 Fitting SMPL to images
07: Dec. 14, 1415-1600 Lect. Hall, MvL 6 Fitting SMPL to IMUs
08: Dec. 21, 1415-1600 Lect. Hall, MvL 6 Vertex based Clothing Models
09: Jan. 11, 1415-1600 Lect. Hall, MvL 6 Neural Implicits and Point based Clothing Models
10: Jan. 18, 1415-1600 - Individual project discussion
11: Jan. 25, 1415-1600 - Individual project discussion
12: Feb. 01, 1415-1600 Lect. Hall, MvL 6 Project presentations


Registration

  • Please register at ILIAS.

Contact

Prof. Dr. Gerard Pons-Moll (mail).
Riccardo Marin (mail).
Xianghui Xie (mail).
Ilya Petrov (mail).