Advanced Topics in Neural Rendering and Reconstruction

Lecture – Winter Semester 2024/2025

Thomas Leimkühler, Rishabh Dabral, Marc Habermann, Vladislav Golyanik, Christian Theobalt

---

Organization  |  Content  |  Resources

---

Top left: Habermann et al., DeepCap 2020. Top right: Laine et al., Modular Primitives for High-Performance Differentiable Rendering, 2020. Bottom left: Rathi et al., 3D-QAE: Fully Quantum Auto-Encoding of 3D Point Clouds, 2023. 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/augmented reality (VR/AR), film production, robotics, and beyond. This course explores advanced topics in this space, emphasizing 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 using differentiable rendering, generative models, morphable models, human reconstruction and synthesis, and quantum visual computing.

---

Organization

---

If 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

Format:	1 lecture per week, in-person attendance.
Time:	Wednesdays from 14:00-16:00
Location:	Lecture hall 003 in E1 3
Credit Points:	3 CP
Lecture Slides:	TBD