Computer Graphics Laboratory ETH Zurich

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.

Prerequisites

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

Administration

Schedule

Date	Name	Topic	Supervisor
Sept 21	Lubor Ladicky, Martin Guay	Introduction and paper assignments
Sept 28	Lubor Ladicky, Martin Guay, Federico Perazzi	Example Talk
Oct 12	Felice Serena	Real time high fidelity facial performance capture	Samir Mahmalat
Oct 12	Simone Guggiari	Trajectory Optimization for Full-Body Movements with Complex Contacts	Dominik Borer
Oct 19	Pontus Andersson	Perceptual Losses for Real-Time Style Transfer and Super-Resolution	Simone Meyer
Oct 19	Moyuan Zhou	Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks	Aziz Djelouah
Oct 26	Yilun Yu	VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera	Cengiz Oztirelli
Oct 26	Petur-Helgi Einarsson	Phase-Functioned Neural Networks for Character Control	Dominik Borer
Nov 2	Michelle Barnett	Accurate Optical Flow via Direct Cost Volume Processing	Martin Oswald
Nov 2	Sasha Pagani	Direct Sparse Odometry	TBD
Nov 9	Christoph Maurhofer	DeepLoco: Dynamic Locomotion Skills Using Hierarchical Deep Reinforcement Learning	Martin Guay
Nov 9	Claudio Rothlisberger	Emergence of Locomotion Behaviours in Rich Environments	Martin Guay
Nov 16	Andreea Radoescu	Unrolling the shutter	TBD
Nov 16	Prashanth Chandran	Modeling Surface Appearance from a Single Photograph using Self-augmented Convolutional Neural Networks	Daniel Thul
Nov 23	Xianyao Zhang	Densely Connected Convolutional Networks	Yifan Wang
Nov 23	Spyridon Angelopoylos	Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network	Yifan Wang

Seminar Papers