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 | 21.09.2023 | -- | no seminar |
| 2 | 28.09.2023 | -- | no seminar |
| 3 | 05.10.2023 | -- | no seminar |
| 4 | 12.10.2023 | Mert Albaba | XSkill: Cross Embodiment Skill Discovery |
| 4 | 12.10.2023 | Artur Grigorev | GarmentCode: Programming Parametric Sewing Patterns |
| 5 | 19.10.2023 | Egor Zakharov | Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis |
| 5 | 19.10.2023 | Lixin Xue | Neuralangelo: High-Fidelity Neural Surface Reconstruction |
| 6 | 26.10.2023 | Zijian Dong | Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion |
| 6 | 26.10.2023 | Zijian Dong | AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose |
| 7 | 02.11.2023 | Gengyan Li | Mixture of Volumetric Primitives for Efficient Neural Rendering |
| 7 | 02.11.2023 | Mert Albaba | Ase: Large-scale reusable adversarial skill embeddings for physically simulated characters |
| 8 | 09.11.2023 | -- | no seminar |
| 9 | 16.11.2023 | -- | no seminar |
| 10 | 23.11.2023 | Yufeng Zheng | Multi-View Reconstruction using Signed Ray Distance Functions (SRDF) |
| 10 | 23.11.2023 | Yufeng Zheng | Control4D: Dynamic Portrait Editing by Learning 4D GAN from 2D Diffusion-based Editor |
| 11 | 30.11.2023 | Hsuan-I Ho | Learning Locally Editable Virtual Humans |
| 11 | 30.11.2023 | Hsuan-I Ho | Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models |
| 12 | 07.12.2023 | Chen Guo | Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition |
| 12 | 07.12.2023 | Zicong Fan | TOCH: Spatio-Temporal Object Correspondence to Hand for Motion Refinement |
| 13 | 14.12.2023 | -- | The eyes have it: An integrated eye and face model for photorealistic facial animation |
| 13 | 14.12.2023 | -- | Learning joint reconstruction of hands and manipulated objects |
| 14 | 21.12.2023 | -- | no seminar |