Hauptseminar Computer Graphics and Visualization (SS 2025)
Information
Supervisor | Prof. Dr. S. Gumhold |
Organizer | David Groß |
SWS | 0/2/0 |
Time & Place | Thursday 2. DS 9:20 a.m. in APB/E009/U (see schedule below) |
Modules |
|
Registration
Please enroll in the Opal course and in Selma to participate in the seminar!
Topic selection closed! (Topic selection: Please fill out this DuD-Poll to select a preferred and alternative topic. If you want to team up with other students, make sure all team members select the same topics. Collisions in topic assignment will be resolved on a first come, first served basis. Please note that a single topic will be given out to at most 3 students and the total number of participants is limited to 18.)
Schedule
General appointments in the seminar room are on the following dates:
- 17.04.2025, 9:20 a.m.
Kickoff (organization, presentation of topics, announcing teams)
Slides available after lecture. - 24.04.2025., 9:20 a.m.
Lecture on good practices in scientific writing
Slides available after lecture.
Motivation
One of the most important aspects of science is to share results with others. In most cases, this is accomplished by publishing a paper in a scientific journal. High-quality scientific writing is therefore crucial for a successful research career. In this seminar, the participants will be introduced to scientific research in general and the essential aspects of literature study. The final goal is to write a review report on one of the topics below which will be presented at the end of the semester.
Topic: Neural Graphics
Recent advancements in machine learning have enabled ever more complex models and efficient inference. In the field of computer graphics, neural networks have been successfully employed to perform rendering tasks like computing physically based lighting, texture compression or image upscaling. The latest generation of graphics cards even allows using specialized hardware for neural network inference to augment the traditional rendering pipeline. Available seminar topics connected to neural rendering and graphics are given in the following list:
- Applications of Machine Learning in Real-Time Rendering
- Deferred Neural Rendering
- Rendering of Gaussian Splats
- Interactive and Immersive Manipulation of Gaussian Splats
- Learned Scene Representations
- Generation of 3D Models from Text Descriptions
Task
Students will write a summary report on one of the given subtopics. Depending on the number of total participants, we will ask you to work in groups of up to 3 people. The report has to be written in english (communication in german might be possible depending on the tutor). Successful participation requires:
- A 1-2 page written overview of your topic.
- A graded written review in two-column paper format (approximately 6 pages per group member).
- A graded presentation (10-15 min per group member + 20 min discussion).