Physical and neural methods for realistic image generation

For appointments please consult the ZEuS of the Universität Konstanz. The exercise can be found here.

This is a directed studies course (exercise) in which students have to read the literature and do the practical course work. We will meet from time to time and discuss the content of the books. Please send in addition to registering for the course an email to Prof. Deussen.

Description

Learning Content:

This course teaches methods for generating photorealistic images of virtual scenes. To achieve this the light propagation within the scene has to be simulated using global illumination.

Lecture Content:

Introduction to Raytracing
- Basic algorithm, extensions, data structures
Light transport and global illumination
- Rendering equation, global light transport
- Sampling, Monte-Carlo Integration
- Path-Tracing, Particle Tracing
- Radiosity
Radiosity
- light transport revisited
- creating the equation systems / Form Factors
General aspects
- Finite element methods
- plenoptic function / image-based rendering
- Holography
Neural creation of images

Qualified Students:

Information Engineering students, bachelor in-depth lectures or master program

Prerequisites:

Basics on computer graphics, programming skills (C++)

Credit requirements:

oral (20min) or written (60min) examination, depending on number of students

Examination date:

First date: tba

Credits:

Successful participation yields 6 ECTS