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 (use ETH credentials to access the file).
All other students read the paper and submit questions they have about the paper before the presentation.
Schedule
| Wk. | Date | TA | Paper |
|---|---|---|---|
| 2 | 26.09.2024 | Chengwei Zheng | 3D Gaussian Splatting for Real-Time Radiance Field Rendering |
| 2 | 26.09.2024 | Zijian Dong | Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images |
| 3 | 03.10.2024 | Gengyan Li | NPGA: Neural Parametric Gaussian Avatars |
| 3 | 03.10.2024 | Mert Albaba | Eureka: Human-Level Reward Design via Coding Large Language Models |
| 4 | 10.10.2024 | Zijian Dong | GaussianHair: Hair Modeling and Rendering with Light-aware Gaussians |
| 4 | 10.10.2024 | Tianjian Jiang | Zero-1-to-3: Zero-shot One Image to 3D Object |
| 5 | 17.10.2024 | Egor Zakharov | DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis |
| 5 | 17.10.2024 | Egor Zakharov | Sapiens: Foundation for Human Vision Models |
| 6 | 24.10.2024 | Manuel Kaufmann | TryOnDiffusion: A Tale of Two UNets |
| 6 | 24.10.2024 | Vanessa Sklyarova | NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads |
| 7 | 31.10.2024 | Lixin Xue | Single-Shot High-Quality Facial Geometry and Skin Appearance Capture |
| 7 | 31.10.2024 | Yufeng Zheng | Dream-in-4D: A Unified Approach for Text- and Image-guided 4D Scene Generation |
| 8 | 07.11.2024 | -- | no seminar |
| 9 | 14.11.2024 | -- | no seminar |
| 10 | 21.11.2024 | Gengyan Li | GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians |
| 10 | 21.11.2024 | Tianjian Jiang | TripoSR: Fast 3D Object Reconstruction from a Single Image |
| 11 | 28.11.2024 | Manuel Kaufmann | Physical Non-inertial Poser (PNP): Modeling Non-inertial Effects in Sparse-inertial Human Motion Capture |
| 11 | 28.11.2024 | Yufeng Zheng | HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics |
| 12 | 05.12.2024 | Lixin Xue | DUSt3R: Geometric 3D Vision Made Easy |
| 12 | 05.12.2024 | Mert Albaba | Diffusion Policy: Visuomotor Policy Learning via Action Diffusion |
| 13 | 12.12.2024 | Chengwei Zheng | 4K4D: Real-Time 4D View Synthesis at 4K Resolution |
| 13 | 12.12.2024 | Vanessa Sklyarova | HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles |
| 14 | 19.12.2024 | -- | no seminar |