Virtual Humans
Course: Winter Semester 2026/27
Continuous Learning of Multimodal Data Streams
University of Tübingen
|
|
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:
The code for the course's interactive demos is available in the vh-toolbox repository.
The following topics will be covered in the course:
- Body and Clothing Models.
- Rotations, Surface Parameterization etc.
- Neural Implicits and Gaussian Splatting based Human Models.
- Human Behaviour Capture and Synthesis.
- Human Skill Transfer to Robots.
The code for the course's interactive demos is available in the vh-toolbox repository.
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 are:
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
- Lectures: Lecture Hall (ground floor), Maria-von-Linden Strasse 6 (MvL6). Tuesday, 12:00-14:00.
- Tutorials: Room A207, Maria-von-Linden Strasse 1 (MvL1). Monday, 12:00-14:00.
Assignments
There will be 3 bi-weekly assignments and a research project.Exam
The final exams will take place on-site in Tüebingen, 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.Exam date: First exam: TBA, Second exam: TBA. Location: TBA.
Schedule for Lectures
The lecture happens every Tuesday 12-14pm in the lecture hall (ground floor) of Maria-von-Linden Strasse 6 (MvL6), starting on October 13, 2026.| # | Date & Time | Location | Title | Material |
|---|---|---|---|---|
| 01: | Oct. 13, 1200-1400 | MvL6 | Organization and Introduction to Body Models | slides |
| 02: | Oct. 20, 1200-1400 | MvL6 | Image Formation and Rotations | slides |
| 03: | Oct. 27, 1200-1400 | MvL6 | Surface Representations and Procrustes Alignment | |
| 04: | Nov. 3, 1200-1400 | MvL6 | ICP, Non-rigid Alignment & Vertex-based Models | |
| 05: | Nov. 10, 1200-1400 | MvL6 | Fitting SMPL to Scans | |
| 06: | Nov. 17, 1200-1400 | MvL6 | Fitting SMPL to Images | |
| 07: | Nov. 24, 1200-1400 | MvL6 | Fitting SMPL to IMUs | |
| 08: | Dec. 1, 1200-1400 | MvL6 | Vertex-based Clothing Models | |
| 09: | Dec. 8, 1200-1400 | MvL6 | Neural Implicits and Point-based Clothing Models | |
| 10: | Dec. 15, 1200-1400 | MvL6 | NeRF, Gaussian Splatting and Humans | |
| 11: | Dec. 22, 1200-1400 | MvL6 | Human Behaviour Capture | |
| -- | Dec. 29, Jan. 5 | - | No lecture (holidays) | |
| 12: | Jan. 12, 1200-1400 | MvL6 | Human Behaviour Synthesis & Diffusion Models for Motion | |
| 13: | Jan. 19, 1200-1400 | MvL6 | Physics-based Methods, Policy Learning, Transfer to Robots |
Schedule for Tutorials
The tutorials happen every Monday 12-14pm in Room A207, Maria-von-Linden Strasse 1 (MvL1), starting on October 19, 2026.| # | Date & Time | Location | Title | Material |
|---|---|---|---|---|
| 01: | Oct. 19, 1200-1400 | MvL1, A207 | Introduction | material |
| 02: | Oct. 26, 1200-1400 | MvL1, A207 | Assignment 01 release | |
| 03: | Nov. 2, 1200-1400 | MvL1, A207 | Discussion | |
| 04: | Nov. 9, 1200-1400 | MvL1, A207 | Assignment 02 release | |
| 05: | Nov. 16, 1200-1400 | MvL1, A207 | Discussion | |
| 06: | Nov. 23, 1200-1400 | MvL1, A207 | Cluster Intro + Project Proposal | |
| 07: | Nov. 30, 1200-1400 | MvL1, A207 | Discussion | |
| 08: | Dec. 7, 1200-1400 | MvL1, A207 | Discussion | |
| 09: | Dec. 14, 1200-1400 | MvL1, A207 | Individual project discussion | |
| 10: | Jan. 11, 1200-1400 | MvL1, A207 | Project: midterm presentation | |
| 11: | Jan. 18, 1200-1400 | MvL1, A207 | Individual project discussion | |
| 12: | Jan. 25, 1200-1400 | MvL1, A207 | Individual project discussion | |
| 13: | Feb. 1, 1200-1400 | MvL1, A207 | Individual project discussion | |
| 14: | Feb. 8, 1200-1400 | MvL1, A207 | Final Project presentations |
Registration
- Registration will be open from September 22, 2026. We plan to admit 30 students in total, so first come first serve.
- Please register on ILIAS website.