Overview
The learning objective is to analyze selected research papers published at top computer vision and machine learning venues. A key focus will be placed on identifying and discussing open problems and novel solutions in this space. The seminar will achieve this via several components: reading papers, technical presentations, writing analysis and critique summaries, class discussions, and exploration of potential research topics. In this seminar we will discuss state-of-the-art literature on human-centric computer vision topics including but not limited to human pose estimation, hand and eye-gaze estimation as well as generative modeliing of detailed human activities.
Goal
The goal of the seminar is not only to familiarize students with exciting new research topics, but also to teach basic scientific writing and oral presentation skills. The seminar will have a different structure from regular seminars to encourage more discussion and a deeper learning experience.
We will treat papers as case studies and discuss them in-depth in the seminar. Once per semester, every student will have to take one of the following roles:
- Presenter: Give a presentation about the paper that you read in depth.
- Reviewer: Write a critical review of the paper following this template.
All other students read the paper and submit questions they have about the paper before the presentation.
Schedule
| Wk. | Date | TA | Paper |
|---|---|---|---|
| 1 | 22.09.2021 | -- | no seminar |
| 2 | 29.09.2021 | -- | no seminar |
| 3 | 06.10.2021 | -- | no seminar |
| 4 | 13.10.2021 | Adrian Spurr | End-to-End Human Pose and Mesh Reconstruction with Transformers |
| 4 | 13.10.2021 | Adrian Spurr | Hand Pose Estimation via Latent 2.5D Heatmap Regression |
| 5 | 20.10.2021 | Jie Song | SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes |
| 5 | 20.10.2021 | Jie Song | SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks |
| 6 | 27.10.2021 | Gengyan Li | EyeNeRF: a hybrid representation for photorealistic synthesis, animation and relighting of human eyes |
| 6 | 27.10.2021 | Gengyan Li | VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relighting |
| 7 | 03.11.2021 | Mert Albaba | R3M: A Universal Visual Representation for Robot Manipulation |
| 7 | 03.11.2021 | Mert Albaba | AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting |
| 8 | 10.11.2021 | -- | no seminar |
| 9 | 17.11.2021 | -- | no seminar |
| 10 | 24.11.2021 | Chen Guo | Differentiable Dynamics for Articulated 3d Human Motion Reconstruction |
| 10 | 24.11.2021 | Chen Guo | HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video |
| 11 | 01.12.2021 | Sammy Christen | Embodied Scene-aware Human Pose Estimation |
| 11 | 01.12.2021 | Sammy Christen | ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters |
| 12 | 08.12.2021 | Artur Grigorev | Efficient Geometry-aware 3D Generative Adversarial Networks |
| 12 | 08.12.2021 | Artur Grigorev | Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing |
| 13 | 15.12.2021 | Hsuan-I | Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images |
| 13 | 15.12.2021 | Hsuan-I | Video2StyleGAN: Disentangling Local and Global Variations in a Video |
| 14 | 22.12.2019 | -- | no seminar |