Seminar Computergraphik WS'26/27
Seminar

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 their 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 5 students.

Important Dates

All dates listed here must be adhered to. In order to successfully complete the module, it is mandatory to fullfill the deadlines, and attend ALL events in person.

• From 09.07.2026 to 14.07.2026: Registration process via Stud.IP
• Until 12.10.2026: Submission of topic requests via email
• 21.10.2026, 11:15: Kick-Off Meeting (G30, ICG)
• 02.11.2026: End of the deregistration period 
• 17.11.2026: Submission of the written paper
• 01.12.2026: Submission of the review report
• 15.12.2026: Submission of the revised paper
• Until 15.01.2027: Trial presentation
• 21.01.2027: Submission of the presentation slides
• 22.01.2027, 09:00 - 11:00: Presentations I - Block Event
• 29.01.2027, 09:00 - 11:00: Presentations II- Block Event
  
  

Registered students have the possibility to deregister until 2 weeks after the start of the lectures (i.e., 2.11.26) 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 12.10.26, 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, as well as attendance to all in-person events, 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

Tips on How to Give a Talk:

•    Giving a research talk. Short pdf with recommendations by Fredo Durand (MIT CSAIL)

•    How to give a talk (that doesn't put your audience to sleep). Slides by Ramesh Raskar (MIT Media Lab)
  
  

Topics

1. Beyond Spherical Harmonics: Rethinking Appearance Models for Radiance Reconstruction
   Ewa Miazga, Jorge Condor, Piotr Didyk
   EGSR 2026
   Advisor: Florian Hahlbohm
   
   This paper investigates alternative appearance models for representing view-dependent effects in radiance fields and Gaussian Splatting. The project explores how compact spherical functions can improve the reconstruction of reflections and highlights while reducing memory and computational costs.
   
   
   
2. ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splatting
   Yuetao Li, Zijia Kuang, Ting Li, Qun Hao, Zike Yan, Guyue Zhou, Shaohui Zhang
   IEEE RA-L 2025
   Advisor: Junbo Li
   
   Active Scene Reconstruction is an interdisciplinary research area that focuses on solving viewpoint selection and scene reconstruction problems simultaneously. The primary objective is to attain a high coverage rate and superior reconstruction quality of the explored scene. 3D Gaussian splatting (3DGS) is a prevalent technique that has the capacity to reconstruct a scene with remarkable speed while preserving optimal quality. The present paper proposes a novel approach that utilizes high-speed and high-quality rendering from 3DGS and integrates it into the active scene reconstruction pipeline, in conjunction with Voronoi-graph-based path planning. This innovative integration results in state-of-the-art reconstruction outcomes.
   
   
   
3. Eulerian Gaussian Splatting
   Mia Gaia Polansky, George Kopanas, Stephan Garbin, Todd Zickler, Dor Verbin
   CVPR 2026
   Advisor: Timon Scholz
   
   Traditional 3DGS-based methods for scene reconstruction directly optimize Gaussian parameters. This process typically involves heuristics to identify primitives which need to be duplicated or deleted, while also relying on good initializations to achieve optimal quality. By instead optimizing a grid-based probability distribution, Eulerian Gaussian Splatting can optimize a scene without these heuristics from a fully random initialization, while achieving state-of-the-art image metrics. Since the scene is rendered by first drawing samples from this probability distribution, inference time is unaffected, as the final set of primitives can be pre-computed after training.
   
   
   

4. Real-time Rendering with a Neural Irradiance Volume
   Arno Coomans, Giacomo Nazzaro, Edoardo A. Dominici, Christian Döring, Floor Verhoeven, Konstantinos Vardis, and Markus Steinberger
   EUROGRAPHICS 2026
   Advisor: Felix Lehner
   
   Neural Irradiance Volume (NIV) is a neural-based method for real-time diffuse global illumination that replaces traditional probe grids with a compact, adaptive neural representation. Compared to probe-based approaches, it significantly reduces memory usage, eliminates common artifacts, and improves quality while supporting dynamic lighting effects. NIV achieves these benefits with fast inference (about 1 ms per frame), low memory requirements, and without requiring ray tracing or denoising.
   
   

5. MSCD-GS: Motion-Separated Cooperative Deblurring Dynamic Reconstruction via Gaussian Splatting
   Yongjian Liao et al.
   CVPR 2026
   Advisor: JP Tauscher

This project develops a Gaussian Splatting method for reconstructing dynamic 3D scenes from motion-blurred videos captured with a standard camera. It separately models the movement of static and moving parts of the scene and combines image deblurring with 4D reconstruction, allowing both processes to improve each other. Experiments show that the method produces sharper and higher-quality reconstructions than existing approaches when the input videos contain strong motion blur.

Advisors

Florian Hahlbohm

Junbo Li

Timon Scholz

Felix Lehner

JP Tauscher