Master-Seminar – Deep Learning in Computer Graphics (IN2107, IN0014)
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.
- It is only allowed to miss a single time-slot. Missing a second one means failing the seminar. If you have to miss any, please let us know in advance.
- You will present your topic in English, and the talk should last 30 minutes. After that, a discussion session for ca. 10 minutes will follow.
- The slides should be structured according to your presentation. You can use any layout or template you like.
- Plagiarism is important; 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.
- Be ready in advance. We suggest testing the machines you are going to use before the lecture starts. You can bring your laptop or ask us one (also any converter you need for the projector) in advance. A laser pointer will be provided, so you can use if you want.
- 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 within two weeks after the talk, i.e., by 23:59 on Monday. When you send the report, please send the final slides (PDF) together.
- 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.
|16 March 2018||Deadline for sending an e-mail with 3 preferences|
|23 March 2018||Notification of assigned paper|
|09 Apr 2018||No Lecture||Preparation|
|16 Apr 2018||Dominik Fuchsgruber||2016, Dong et al., Image Super-Resolution Using Deep Convolutional Networks, IEEE Trans. Pattern Anal. Mach. Intell.|
|16 Apr 2018||Mert Ülker||2017, Dahl et al., Pixel Recursive Super Resolution, arXiv.org|
|23 Apr 2018||Vladimir Poliakov||2014, Goodfellow et al., Generative Adversarial Networks, Advances in Neural Information Processing Systems 27|
|23 Apr 2018||Daniel Matter||2015, Mnih et al., Human-Level Control Through Deep Reinforcement Learning, Nature|
|Cancelled||Ahmad Tahir||2015, Gryka et al., Learning to Remove Soft Shadows, ACM Trans. Graph.|
|30 Apr 2018||Konstantin Weißenow||2017, Li et al., Deep Extraction of Manga Structural Lines, ACM Trans. Graph.|
|07 May 2018||Khushbu Saxena||2016, Ruder et al., Artistic Style Transfer for Videos, GCPR|
(optional) 2015, Gatys et al., A Neural Algorithm of Artistic Style, arXiv.org
|07 May 2018||Maheswaran Rajesh||2017, Wang et al., O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis, ACM Trans. Graph.|
|14 May 2018||Martin Eisenmann||2017, Chu and Thuerey, Data-driven Synthesis of Smoke Flows with CNN-based Feature Descriptors, ACM Trans. Graph.|
|14 May 2018||Fabian Kilger||2018, Xie et al., tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow, arXiv.org|
|21 May 2018||No Talk||Whit Monday|
|28 May 2018||Jeremias Bohn||2016, Peng et al., Terrain-adaptive Locomotion Skills Using Deep Reinforcement Learning, ACM Trans. Graph.|
|28 May 2018||Moritz Becher||2017, Holden et al., Phase-functioned Neural Networks for Character Control, ACM Trans. Graph.|
|04 Jun 2018||Jan Ahlbrecht||2017, Suwajanakorn et al., Synthesizing Obama: Learning Lip Sync from Audio, ACM Trans. Graph.|
|04 Jun 2018||Kaan Bagci||2017, Karras et al., Audio-driven Facial Animation by Joint End-to-end Learning of Pose and Emotion, ACM Trans. Graph.|
|11 Jun 2018||Kilian Schmidt||2017, Gharbi et al., Deep Bilateral Learning for Real-time Image Enhancement, ACM Trans. Graph.|
|11 Jun 2018||Malte Schmitz||2017, Bako et al., Kernel-predicting Convolutional Networks for Denoising Monte Carlo Renderings, ACM Trans. Graph.|
You can access the papers through TUM library's eAccess.
- Book: Bishop, Pattern Recognition and Machine Learning
- Book: Hastie et al., The Elements of Statistical Learning
- Online: Nielsen, Neural Networks and Deep Learning
- Online: Ruder, An Overview of Gradient Descent Optimization Algorithms