Logos of MPI Informatik

Visual Computing and Artificial Intelligence Department

Advanced Topics in Neural Rendering and Reconstruction

Lecture – Summer Semester 2026

Thomas Leimkühler, Rishabh Dabral, Marc Habermann, Briac Toussaint, Lin Geng Foo, Christian Theobalt


Organization  |  Content

teaser
Top left: Dabral et al., MoFusion, 2023. Top right: Mildenhall et al., NeRF, 2020. Bottom left: Habermann et al., DeepCap, 2020. Bottom right: Yang et al., Diffusion Models, 2024.

Course Description

Neural rendering and reconstruction form the foundation of digitizing the physical world, with applications in virtual and augmented reality (VR/AR), film production, robotics, and beyond. This course explores advanced topics in this area, with an emphasis on data-driven approaches using neural models. After reviewing the basics of computer graphics and machine learning, we will delve into 3D scene representation and reconstruction, including differentiable rendering, generative scene, image, and video models, morphable models, and human reconstruction and synthesis.


Organization

If you have questions about this lecture, please contact us via thomas.leimkuehler@mpi-inf.mpg.de.

Prerequisites

The course is tailored towards students of Visual Computing (M.Sc.), Computer Science (M.Sc.), and Data Science and Artificial Intelligence (M.Sc.).

It is preferred, but not necessarily required, that students have already studied Image Processing and Computer Vision and Computer Graphics 1, or something equivalent.


Schedule and other details

Registration: Please register in the CMS. Please do not forget to register for the exam in the HISPOS system.
Format: 1 lecture per week, in-person attendance
Time: Thursdays, 14:15-15:45
Location: E1.3, lecture hall 003
Credit Points: 3 CP
Exam: Final exam: 05.08.2026, 14:00-16:00.
Re-exam: 26.08.2026, 10:00-12:00.
Both exams will be held in E1.3, lecture hall 001.
Lecture Slides: Available for download in the CMS for registered students