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

Philipp Holl, Bjoern List and Nils Thuerey

Time, Place Tuesdays 14:00-16:00 in room: MI 02.13.010

Begin

October 17.,  2023

Kick-Off: Tuesday, October 17., 2023 at 14:00

On Site in room: MI 02.13.010

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 talks. 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 (2 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 Tuesday.
  • 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 20 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 after the talk.

Topics

Paper Number Paper
1 2017, Chaitanya et al., Interactive reconstruction of Monte Carlo image sequences using a recurrent denoising autoencoder
2   2021, Işık et al., Interactive Monte Carlo denoising using affinity of neural features
3   2019, Chu et al., Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation, arXiv.org
4   2021, Karras et al., Alias-free generative adversarial networks
5   2020, Wang et al., Attribute2Font: Creating Fonts You Want From Attributes, ACM Trans. Graph
6   2022, Lin et al., 3D GAN Inversion for Controllable Portrait Image Animation
7   2022, Saharia et al., Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
8   2023, Pan et al. , Drag your gan: Interactive point-based manipulation on the generative image manifold
9 2019, Meka et al., Deep Reflectance Fields - High-Quality Facial Reflectance Field Inference From Color Gradient Illumination, ACM Trans. Graph
10   2020, Dupont et al., Equivariant Neural Rendering, ICML
11   2020, Kopf et al., One Shot 3D Photography, ACM Trans. Graph
12   2020, Mildenhall et al., Representing Scenes as Neural Radiance Fields for View Synthesis
13   2021, Yin et al., Learning to Recover 3D Scene Shape from a Single Image, CVPR
14 2022, Chen et al., TensoRF: Tensorial Radiance Fields
15 2022, Mueller et al., Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
16 2023, Kerbl et al., 3D Gaussian Splatting for Real-Time Radiance Field Rendering
17 2021, Müller et al., Real-time neural radiance caching for path tracing
18 2022, Franz et al., Global Transport for Fluid Reconstruction with Learned Self-Supervision
19 2022, Xie et al., TemporalUV: Capturing Loose Clothing with Temporally Coherent UV Coordinates
20 2022, Vicini et al., Differentiable Signed Distance Function Rendering
21 2020, Xiao et al., Neural Supersampling for Real-Time Rendering, ACM Trans. Graph.
22 2019, Choi & Kweon, Deep Iterative Frame Interpolation for Full-frame Video Stabilization, arXiv.org
23 2023, Blattman et al., Align your latents: High-resolution video synthesis with latent diffusion models
24 2022, Harvey et al., Flexible diffusion modeling of long videos

Presentation Schedule

Date Paper Paper ID Student    
17.10.2023 INTRO LECTURE        
24.10.2023 no seminar        
31.10.2023 no seminar        
07.11.2023 2017, Chaitanya et al., Interactive reconstruction of Monte Carlo image sequences using a recurrent denoising autoencoder 1 Hkiri    
07.11.2023 2021, Işık et al., Interactive Monte Carlo denoising using affinity of neural features 2 Kobalt    
14.11.2023 no seminar        
21.11.2023 2023, Kerbl et al., 3D Gaussian Splatting for Real-Time Radiance Field Rendering 21 Wargitsch    
21.11.2023 2022, Franz et al., Global Transport for Fluid Reconstruction with Learned Self-Supervision 23 Kuang    
28.11.2023 please attend talk by Prof. Hanrahan at 14:00 in HS1 (FMI)        
05.12.2023 2021, Karras et al., Alias-free generative adversarial networks 4 Xu    
05.12.2023 2022, Lin et al., 3D GAN Inversion for Controllable Portrait Image Animation 6 Mandarapu    
12.12.2023 2020, Dupont et al., Equivariant Neural Rendering, ICML 10 Aytekin    
12.12.2023 2020, Mildenhall et al., Representing Scenes as Neural Radiance Fields for View Synthesis 12 Bellaaj    
19.12.2023 no seminar        
26.12.2023 no seminar        
02.01.2024 no seminar        
09.01.2024 2022, Franz et al., Global Transport for Fluid Reconstruction with Learned Self-Supervision 18 Richter    
09.01.2024 2023, Kerbl et al., 3D Gaussian Splatting for Real-Time Radiance Field Rendering 16 Kong    
16.01.2024 2020, Wang et al., Attribute2Font: Creating Fonts You Want From Attributes, ACM Trans. Graph 5 Chang    
16.01.2024 2022, Vicini et al., Differentiable Signed Distance Function Rendering 20 Vogel    
           
           
           
         

References