Computer Graphics Laboratory ETH Zurich


Seminar 'Advanced Topics in Computer Graphics and Vision' - AS 21

Page still under construction!

Course Topics

This seminar covers advanced topics in visual computing, including both seminal research papers as well as the latest research results. Topics include data-driven modeling and animation, image based rendering, real-time vision & graphics, physical simulation and generative models, visual perception, computational photography, video synthesis, and others.

Course Setup

Every participant has to present one of the papers presented in the first session. Additionally, you are required to read the paper that is presented in class beforehand and participate in a discussion during the seminar. An assistant will provide support when preparing the slides and in case technical questions arise.

Important remarks

  • Participants who registered to the course and selected a paper have to present their paper during the semester. In addition each participant has to attend all presentations (3 misses allowed).
    In case these requirements are not met, the course is not passed (fail score).
  • Participants are only allowed to unregister the course before they have chosen a paper to present.
  • Participants who are not registered to the course (e.g. because there are no more free slots), are welcome to attend the first session to fill empty slots.
  • It is not allowed to use the original slides from the author (please prepare the slides to fit an aspect ratio of 16:10).

Learning Objectives

The goal is to get an in-depth understanding of actual problems and research topics in the field of visual computing as well as improve presentations and critical analysis skills.


The "Visual Computing", "Introduction to Computer Graphics" and "Computer Vision I" courses are recommended, but not mandatory.


Number 252-5701-00L
Lecturers Prof. Dr. Marc Pollefeys
Prof. Dr. Olga Sorkine-Hornung
Prof. Dr. Siyu Tang
Assistants Baran Gözcü
Yan Zhang Daniel Barath
Location CAB G 56, Thursday, 14-16
ECTS Credits 2
Exam Graded semester performance


Date Name Topic Supervisor
Sept 23 Introduction and paper assignments
Sept 30 Example Talk
Oct 07 Franz Knobel DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows Luca Cavalli
Oct 14 Joel Neuner-Jehle GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds Till Schnabel
Oct 14 Lea Reichardt Neural complex luminaires: Representation and rendering Xianyao Zhang
Oct 21 Rajat Thakur Superpoint: Self-supervised interest point detection and description Luca Cavalli
Oct 21 Junting Chen Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphs Iro Armeni
Oct 28 Michael Keller Neural Scene Graph Rendering Till Schnabel
Oct 28 Tamara Gini Blurry video frame interpolation Denys Rozumnyi
Nov 04 Oguzhan Ilter An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale Sergey Prokudin
Nov 04 Martina Kessler Lagrangian Neural Style Transfer for Fluids Byungsoo Kim
Nov 18 Anna Maria Eggler NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction Baran Gözcü
Nov 18 Andreas Brombach Leveraging photometric consistency over time for sparsely supervised hand-object reconstruction Jonas Hein
Nov 25 Emmanouil Andreopoulos Vins-mono: A robust and versatile monocular visual-inertial state estimator Thomas Moerwald
Nov 25 Tatiana Gerth We are more than our joints: Predicting how 3D bodies move Yan Zhang
Dec 02 Lukas Bösiger SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks Qianli Ma
Dec 02 Mikhail Terekhov USAC: A universal framework for random sample consensus Daniel Barath
Dec 09 Nicholas Simic Wide-Baseline Multi-Camera Calibration using Person Re-Identification Sergey Prokudin
Dec 09 Tianxu An LEAP: Learning articulated occupancy of people Yan Zhang
Dec 16 Chaoyu Du Generative Layout Modeling using Constraint Graphs Iro Armeni