Time, Place Tuesdays 14:00-16:00 in room: MI 02.13.010 Begin 18th., October 2022 Prerequisites Introduction to Deep Learning
Master-Seminar – Deep Learning in Computer Graphics (IN2107, IN0014)
Liwei Chen , Benjamin Holzschuh and Nils Thuerey
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 (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 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 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 after the talk.
Schedule
29-Aug-22 Deregistration due 12-Sept-22 Deadline for sending an e-mail with 4 preferred topics Notification of assigned paper 18-Oct-22 Introduction lecture (updated) 8-Nov-22 First talk
Presentation Schedule
Date Paper Student Name Advisor 8 Nov. 2019, Chu et al., Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation, arXiv.org Cenikj, Nikola Holzschuh 8 Nov.
2019, Hermosilla et al., Deep-learning the Latent Space of Light Transport, arXiv.org Chen, Wen-Ju Chen 15 Nov.
2019, Thies et al., Deferred Neural Rendering: Image Synthesis using Neural Textures, arXiv.org Marzouki, Mohamed Aziz Slim Holzschuh 15 Nov.
2020, Dupont et al., Equivariant Neural Rendering, ICML Melnychuk, Artem Chen 22 Nov.
2019, Choi & Kweon, Deep Iterative Frame Interpolation for Full-frame Video Stabilization, arXiv.org Ghazinour, Mahyar Holzschuh 22 Nov. 2020, Xiao et al., Neural Supersampling for Real-Time Rendering, ACM Trans. Graph. Kuzovoi, Nikita Chen 29 Nov. 2021, Yin et al., Learning to Recover 3D Scene Shape from a Single Image, CVPR Zhuge, Wenzhe Holzschuh 29 Nov. to be confirmed Chaskopoulos, Dimitrios Holzschuh 6 Dec. 2022, Chu et al., Physics Informed Neural Fields for Smoke Reconstruction with Sparse Data Christian, Maxime Louis Gerd Holzschuh 6 Dec. 2022, Mueller et al., Instant Neural Graphics Primitives with a Multiresolution Hash Encoding Simeng, Li Chen 13 Dec. 2022, Saharia et al., Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding Günther, Jakob Holzschuh 13 Dec. 2022, Peng et al., Shape As Points: A Differentiable Poisson Solver Lima Carneiro, Thiago Chen 10 Jan. 2023 2022, Franz et al., Global Transport for Fluid Reconstruction with Learned Self-Supervision Cancelled 10 Jan. 2023 2022, Lin et al., 3D GAN Inversion for Controllable Portrait Image Animation Yu Heng Luo Holzschuh 17 Jan. 2023 2021, Wu et al., Coarse-to-Fine: Facial Structure Editing of Portrait Images via Latent, Space Classifications, ACM Trans. Graph Paloma Escribano Lopez Chen 17 Jan. 2023 2022, Vicini et al., Differentiable Signed Distance Function Rendering Cancelled
Topics
Paper Number Paper Student Name Advisor 1 2019, Chu et al., Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation, arXiv.org Cenikj, Nikola 2
2019, Meka et al., Deep Reflectance Fields - High-Quality Facial Reflectance Field Inference From Color Gradient Illumination, ACM Trans. Graph 3
2019, Hermosilla et al., Deep-learning the Latent Space of Light Transport, arXiv.org Chen, Wen-Ju 4
2019, Werhahn et al., A Multi-Pass GAN for Fluid Flow Super-Resolution, ACM Comput. Graph. Interact. Tech. 5
2019, Thies et al., Deferred Neural Rendering: Image Synthesis using Neural Textures, arXiv.org Marzouki, Mohamed Aziz Slim 6
2020, Dupont et al., Equivariant Neural Rendering, ICML Melnychuk, Artem 7
2020, Luo et al., Consistent Video Depth Estimation, ACM Trans. Graph 8
2019, Choi & Kweon, Deep Iterative Frame Interpolation for Full-frame Video Stabilization, arXiv.org Ghazinour, Mahyar 9 2019, Frühstück et al., TileGAN: Synthesis of Large-Scale Non-Homogeneous Textures, arXiv.org 10
2021, Wang et al.,Rethinking and Improving the Robustness of Image Style Transfer, CVPR 11
2021, Wu et al., Coarse-to-Fine: Facial Structure Editing of Portrait Images via Latent, Space Classifications, ACM Trans. Graph Paloma Escribano Lopez 12
2020, Wang et al., Attribute2Font: Creating Fonts You Want From Attributes, ACM Trans. Graph 13
2021, Chu et al., Learning Meaningful Controls for Fluids, ACM Trans. Graph 14 2020, Xiao et al., Neural Supersampling for Real-Time Rendering, ACM Trans. Graph. Kuzovoi, Nikita 15 2021, Yin et al., Learning to Recover 3D Scene Shape from a Single Image, CVPR Zhuge, Wenzhe 16 2020, Kopf et al., One Shot 3D Photography, ACM Trans. Graph 17 2022, Xie et al., TemporalUV: Capturing Loose Clothing with Temporally Coherent UV Coordinates 18 2022, Chu et al., Physics Informed Neural Fields for Smoke Reconstruction with Sparse Data Christian, Maxime Louis Gerd 19 2022, Lin et al., 3D GAN Inversion for Controllable Portrait Image Animation Yu Heng Luo 20 2022, Vicini et al., Differentiable Signed Distance Function Rendering Jongsul Han 21 2022, Mueller et al., Instant Neural Graphics Primitives with a Multiresolution Hash Encoding Simeng, Li 22 2022, Saharia et al., Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding Günther, Jakob 23 2022, Peng et al., Shape As Points: A Differentiable Poisson Solver Lima Carneiro, Thiago 24 2022, Franz et al., Global Transport for Fluid Reconstruction with Learned Self-Supervision Ronchetti, Lucas Sergio
Topics (copy 1)
No Date Presenter Paper Advisor 1 --- 2020, Kopf et al., One Shot 3D Photography, ACM Trans. Graph --- 2 --- 2021, Wang et al.,Rethinking and Improving the Robustness of Image Style Transfer, CVPR --- 3 2021, Yin et al., Learning to Recover 3D Scene Shape from a Single Image, CVPR Nilam Tathawadekar 4 2021, Wu et al., Coarse-to-Fine: Facial Structure Editing of Portrait Images via Latent Space Classifications, ACM Trans. Graph Georg Kohl 5 2021, Chu et al., Learning Meaningful Controls for Fluids, ACM Trans. Graph Georg Kohl 6 2019, Werhahn et al., A Multi-Pass GAN for Fluid Flow Super-Resolution, ACM Comput. Graph. Interact. Tech. Nilam Tathawadekar 7 2019, Meka et al., Deep Reflectance Fields - High-Quality Facial Reflectance Field Inference From Color Gradient Illumination, ACM Trans. Graph Erik Franz 8 2020, Nilsson & Akenine-Möller, Understanding SSIM, arXiv.org Georg Kohl 9 2019, Frühstück et al., TileGAN: Synthesis of Large-Scale Non-Homogeneous Textures, arXiv.org Erik Franz 10 2019, Thies et al., Deferred Neural Rendering: Image Synthesis using Neural Textures, arXiv.org Erik Franz 11 2020, Kim et al., Lagrangian Neural Style Transfer for Fluids, ACM Trans. Graph. Nilam Tathawadekar 12 2020, Dupont et al., Equivariant Neural Rendering, ICML Nilam Tathawadekar 13 2020, Luo et al., Consistent Video Depth Estimation, ACM Trans. Graph Nilam Tathawadekar 14 2019, Hermosilla et al., Deep-learning the Latent Space of Light Transport, arXiv.org Georg Kohl 15 2020, Wang et al., Attribute2Font: Creating Fonts You Want From Attributes, ACM Trans. Graph Georg Kohl 16 2019, Choi & Kweon, Deep Iterative Frame Interpolation for Full-frame Video Stabilization, arXiv.org Erik Franz 17 --- --- 2020, Xiao et al., Neural Supersampling for Real-Time Rendering, ACM Trans. Graph. --- 18 2019, Chu et al., Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation, arXiv.org Georg Kohl 19 2019, Karras et al., Analyzing and Improving the Image Quality of StyleGAN, arXiv.org Erik Franz 20 --- --- ---
You can access the papers through TUM library's eAccess .
