Seminar Computergraphik SS'25
Seminar
Sascha Fricke
Hörerkreis: Bachelor & Master
Kontakt: seminar@cg.cs.tu-bs.de
Modul: INF-STD-66, INF-STD-68
Vst.Nr.: 4216012, 4216021
Topic: Current Research in Computer Graphics
Content
In the Computer Graphics Seminar we discuss current research results in the field of Computer Graphics. The tasks of the participants are to write up a research report, to review the work of another student in writing, and to later revise and improve their own report to reflect the input gathered from the review. Finally, at the end of the semester and during a block-seminar, each student will give an oral presentation on their respective research reports. This must also be rehearsed beforehand in front of the assigned individual supervisor and his/her suggestions for improvement must be integrated.
Participants
The course is aimed at Bachelor's and Master's students in Computer Science (Informatik), IST, and Business Informatics (Wirtschaftsinformatik), as well as students pursuing their Master in Data Science.
The registration takes place centrally via StudIP. The number of participants is limited to 6 students.
Important Dates
All dates listed here must be adhered to. Attendance at all events is mandatory.
- From 03.02.2025 to 07.02.2025: Registration process via Stud.IP
- Until 02.04.2025: Submission of topic requests
- 09.04.2025, 13:15.: Kick-Off Meeting (G30, ICG) [Slides]
- 21.04.2025: End of the deregistration period
- 11.05.2025: Submission of the written paper
- 25.05.2025: Submission of the review report
- 08.06.2025: Submission of the revised paper
- Until 27.06.2025: Trial presentation
- 03.07.2025: Submission of the presentation slides
- 04.07.2025, 09:00 - 11:00: Presentations - Block Event
- 11.07.2025, 09:00 - 11:00: Presentations - Block Event Part 2
Registered students have the possibility to deregister until 2 weeks after the start of the lectures (i.e., 21.04.25) at the latest. For a successful deregistration, it is necessary to deregister via e-mail with the seminar supervisor (seminar@cg.cs.tu-bs.de).
Registered students, and students on the waiting list, have the possibility to send their top 3 topic requests in order of preference via email to seminar@cg.cs.tu-bs.de until the 02.04.25, so that they will be considered for the topic assignment.
Once a topic has been assigned to the student, all consequent submissions have to be sent by mail to the respective advisor and additionally to seminar@cg.cs.tu-bs.de. If not communicated otherwise, the deadline for all submissions is at 23:59 on the due day.
The respective drop-offs are done by email to seminar@cg.cs.tu-bs.de and if necessary by email to the respective advisor.
If you have any questions about the course, please contact seminar@cg.cs.tu-bs.de.
Format
- The final assignation of topics will be communicated during the Kick-Off event.
- For each topic, the student needs to prepare a report in latex using the ICG Template.
The content of the report is a short summary of the work in one's own words and the elaboration of the main points, with a minimum length of 8 pages. The report should clearly reflect that the topic has been understood and was critically assessed. - Each participant will later write a 1-2 page review on the report of another student (assigned by the seminar's supervisor). For writing the review one should pay particular attention to the comprehensibility and linguistic style of the summary.
- After receiving the review on one's own paper, the student will need to revise and improve their manuscript according to the received feedback.
- For the final presentations, the students can either use their own laptops or one provided by the Institute. If the student needs to use the ICG laptop, they need to contact seminar@cg.cs.tu-bs.de in time, at least two weeks before the presentations.
- The topics will be presented in approximately 20 minute presentations followed by a discussion.
- The language for the presentations can be either German or English.
- The oral presentation, the written paper, and the preparation of the review report, are all mandatory requirements to pass the course successfully.
Files and Templates
- Latex-Template Its use is compulsory.
- Slides-Template Using this template is recommended but not mandatory.
- Review-Template (mandatory usage)
- Kick-Off Slides
Topics
Representing Long Volumetric Video with Temporal Gaussian Hierarchy
Zhen Xu, Yinghao Xu, Zhiyuan Yu, Sida Peng, Jiaming Sun, Hujun Bao, Xiaowei Zhou
SIGGRAPH Asia 2024
Advisor: Florian Hahlbohm
This paper trains a memory-efficient hierarchy of 4D Gaussian primitives from multi-view RGB videos. After training, the representation enables high-quality novel view synthesis at real-time frame rates.Real-time Neural Appearance Models
Tizian Zeltner, Fabrice Rousselle, Andrea Weidlich, Petrik Clarberg, Jan Novák, Benedikt Bitterli, Alex Evans, Tomáš Davidovič, Simon Kallweit, Aaron Lefohn
SIGGRAPH 2024
Advisor: Sascha Fricke
To recreate complex material properties in image synthesis, it is often necessary to layer many different BRDF models with various different textures. This process is very costly both in terms of memory and performance. In a physically accurate Path Tracer this means that for each light bounce, complex material graphs have to be traversed and for each node, complex BRDFs have to be evaluated and textures need to be fetched.
This paper bakes all these operations into latent feature textures that can be evaluated efficiently at runtime, making complex high quality materials possible in real time.OmniGS: Fast Radiance Field Reconstruction using Omnidirectional Gaussian Splatting
Longwei Li, Huajian Huang, Sai-Kit Yeung, Hui Cheng
WACV 2025
Advisor: Junbo Li
3D Gaussian Splatting based method is known to have both good render quality and fast render speed in the field of novel view synthesis. Typically, undistorted images are employed as the training input. This paper proposes a method that allows 360-degree panoramic images (spherical camera model) to be used for 3D scene reconstruction based on 3DGS.CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models
Rundi Wu, Ruiqi Gao, Ben Poole, Alex Trevithick, Changxi Zheng, Jonathan T. Barron, Aleksander Holynski
arXiv Preprint 2024
Advisor: Timon Scholz
CAT4D utilizes diffusion to generate videos from multiple novel viewpoints for a given monocular input video. This allows it to be used as a prior for dynamic scene reconstruction using deforming 3D GaussiansGANtlitz: Ultra High Resolution Generative Model for Multi-Modal Face Textures
Advisor: Felix Lehner
In dieser Forschungsarbeit wird ein Generative Adversarial Network (GAN) vorgestellt, welches Texturen für menschliche Gesichter erzeugen kann. Die vorgestellte Methodik erlaubt das Trainieren des neuronalen Netzes auf kleinen Datensätzen.Are You Human? Investigating the Perceptions and Evaluations of Virtual Versus Human Instagram Influencers
Anika Nissen, Colin Conrad, Aaron Newman
CHI 2023
Advisor: JP Tauscher
Virtuelle Influencer gewinnen auf Instagram an Bedeutung, und werden von Unternehmen zunehmend für Marketingkampagnen genutzt trotzdem sie der aktuellen Studienlage nach als weniger vertrauenswürdig und uncanny wahrgenommen werden, ohne dass die Gründe dafür vollständig verstanden sind.
Dieses Paper führt eine Befragung von 150 Teilnehmern und eine EEG-Studie zur Analyse neuronaler Mechanismen durch. Die Ergebnisse bestätigen die niedrigere Vertrauenswürdigkeit und höhere Uncanniness von Virtuelle Influencern und zeigen, dass EEG-Komponenten nicht die Vertrauenswürdigkeit, sondern die Wahrnehmung von Menschlichkeit, Uncanniness und die Bereitschaft, Empfehlungen zu folgen, beeinflussen. Diese Erkenntnisse eröffnen neue Ansätze für die Forschung von virtuellen Avataren.TBA
Advisor: Susana Castillo
TBA