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:

  1. Presenter: Give a presentation about the paper that you read in depth.
  2. 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