Master-Seminar – Deep Learning in Computer Graphics (IN2107, IN0014)

Benjamin Holzschuh, Hao Wei and Nils Thuerey

Time, Place Wednesdays 12:00-14:00 in room: MI 02.13.010

Begin

Wednesday April 17., 2024

Kick-Off: Tuesday, January 30. 2024 at 15:00

Online via BBB https://bbb.cit.tum.de/nil-djw-hjw

Prerequisites Introduction to Deep Learning

Content

In this course, students will autonomously investigate recent research about machine learning techniques in computer graphics. Independent investigation for further reading, critical analysis, and evaluation of the topic are required.

Requirements

Participants are required to first read the assigned paper and start writing a report. This will help you prepare for your presentation.

Attendance
  • It is only allowed to miss two sessions. If you have to miss any, please let us know in advance, and write a one-page summary about the paper in your own words. Missing the third one means failing the seminar. 
Report
  • A short report (4 pages max. excluding references in the ACM SIGGRAPH TOG format (acmtog) - you can download the precompiled latex template) should be prepared and sent two weeks after the talk, i.e., by 23:59 on Wednesday.
  • Guideline: You can begin with writing a summary of the work you present as a start point; but, it would be better if you focus more on your own research rather than just finishing with the summary of the paper. We, including you, are not interested in revisiting the work done before; it is more meaningful if you make an effort to put your own reasoning about the work, such as pros and cons, limitation, possible future work, your own ideas for the issues, etc.
  • For questions regarding your paper or feedback for a semi-final version of your report you can contact your advisor.
Presentation (slides)
  • You will present your topic in English, and the talk should last 25 to 30 minutes. After that, a discussion session of about 10 minutes will follow.
  • The slides should be structured according to your presentation. You can use any layout or template you like, but make sure to choose suitable colors and font sizes for readability.
  • Plagiarism should be avoided; please do not simply copy the original authors' slides. You can certainly refer to them.
  • The semi-final slides (PDF) should be sent one week before the talk, otherwise the talk will be canceled.
  • We strongly encourage you to finalize the semi-final version as far as possible. We will take a look at the version and give feedback. You can revise your slides until your presentation.
  • The final slides should be sent together with the report after the talk.

Topics

Paper Number Presenter Paper Date Supervisor
1   2019, Chu et al., Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation, arXiv.org    
Özgün 2021, Karras et al., Alias-free generative adversarial networks 05.06.2024 Benjamin
Li 2020, Wang et al., Attribute2Font: Creating Fonts You Want From Attributes, ACM Trans. Graph 19.06.2024 Hao
Yetistiren 2022, Lin et al., 3D GAN Inversion for Controllable Portrait Image Animation 22.05.2024 Benjamin
Salkic 2022, Saharia et al., Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding 19.06.2024 Benjamin
Lazar 2023, Pan et al. , Drag your gan: Interactive point-based manipulation on the generative image manifold 05.06.2024 Hao
  2020, Dupont et al., Equivariant Neural Rendering, ICML    
L. Moersler 2020, Mildenhall et al., Representing Scenes as Neural Radiance Fields for View Synthesis 08.05.2024 Hao
Bauer 2021, Yin et al., Learning to Recover 3D Scene Shape from a Single Image, CVPR 29.05.2024 Benjamin
10   2022, Chen et al., TensoRF: Tensorial Radiance Fields    
11 P. Moersler 2022, Mueller et al., Instant Neural Graphics Primitives with a Multiresolution Hash Encoding 26.06.2024 Hao
12 Hutter 2023, Kerbl et al., 3D Gaussian Splatting for Real-Time Radiance Field Rendering 17.07.2024 Benjamin
13 Rozhdestvenskii 2021, Müller et al., Real-time neural radiance caching for path tracing 03.07.2024 Benjamin
14 Kayabek 2022, Franz et al., Global Transport for Fluid Reconstruction with Learned Self-Supervision 03.07.2024 Hao
15 Decker 2022, Vicini et al., Differentiable Signed Distance Function Rendering 10.07.2024 Benjamin
16 Gao 2020, Xiao et al., Neural Supersampling for Real-Time Rendering, ACM Trans. Graph. 08.05.2024 Benjamin
17   2023, Blattman et al., Align your latents: High-resolution video synthesis with latent diffusion models    
18   2023, Peebles et al., Scalable Diffusion Models with Transformers    
19 Pöttke 2021, Radford et al., Learning Transferable Visual Models From Natural Language Supervision 17.07.2024 Hao
20 Kacmazoglu 2020, Ho et al., Denoising Diffusion Probabilistic Models 15.05.2024 Benjamin
21 Winter 2022, Nielsen et al., Physics-Based Combustion Simulation 29.05.2024 Hao
22   2021, John et al., Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers    
23 Ben Hamouda 2021, Ilya et al., MLP-Mixer: An all-MLP Architecture for Vision 22.05.2024 Hao
24 Liu 2021, Dosovitskiy et al., An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 15.05.2024 Hao

25

  2021, Rao et al., Global Filter Networks for Image Classification    
26 Sarica 2022, Hertz et al., Prompt-to-Prompt Image Editing with Cross Attention Control 10.07.2024 Benjamin

References