Computer Graphics Laboratory ETH Zurich

ETH

Seminar 'Advanced Methods in Computer Graphics' - SS 19

Description

Course Topics

This seminar covers advanced topics in visual computing, including both seminal research papers as well as the latest research results. The main topic areas are image and video processing, capture, rendering, visualization, simulation, fabrication as well as machine learning in graphics.

Course Setup

Every participant has to present one of the papers in the list below. 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.

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

Presence

Presence is mandatory to pass the seminar. If a student cannot attend a seminar session, the reason (e.g. medical certificate) has to be given before the session and must be accepted by one of the organizers. More than three missed seminar sessions will cause the student to fail this class. The dates for the presentations can not be moved except there is someone willing to switch.

Grading

The presentation of the selected paper contributes 75% to the final grade. Additionally, the students are required to submit a short abstract of each paper before the class as well as to participate in the group discussions after the presentations. Both will be documented by the organizers and contributes 25% to the final grade.

Organization and Grading

Number 252-5704-00L
Lecturers M. Gross, O. Sorkine-Hornung
Assistants Dr. Vinicius C. Azevedo (vinicius.azevedooinf.ethz.ch), CNB G 102.1

Dr. Tobias Günther (tobias.guentheroinf.ethz.ch), CNB G 102.1

Dr. Jérémy Riviere (jeremy.riviereodisneyresearch.com)
Location CAB G 52, Fridays 13:00-15:00

Links

Schedule

Date Topic Paper Student Supervisor
22-FebIntroduction
01-MarExample
08-MarNo session
15-MarNo session
22-MarMaterialsDisplacement Interpolation using Lagrangian Mass TransportSimon HuberTobias Guenther
High-Contrast Computational Caustic DesignTimo LaudiMarios Papas
29-MarAnimation 1An Empirical Rig for Jaw AnimationValentin SchererGaspard Zoss
A Deep Learning Approach for Generalized Speech AnimationNicholas IngulfsenPaulo Gotardo
05-AprAnimation 2Phase-functioned Neural Networks for Character ControlSimon RingeisenDominik Borer
SMPL: A Skinned Multi-Person Linear ModelMarkus RothDominik Borer
12-AprNo sessionNo session
19-AprNo sessionNo session
26-AprNo sessionNo session
03-MayFluidstempoGAN: A Temporally Coherent, Volumetric GAN for Super-Resolution Fluid FlowTill SchnabelByungsoo Kim
The Affine Particle-In-Cell MethodGengyan LiVinicius Azevedo
10-MayDenoising 1Kernel-Predicting Convolutional Networks for Denoising Monte Carlo RenderingsAlain HostettlerMarco Ancona
Noise2Noise: Learning Image Restoration without Clean DataCavaleri AlexandreAziz Dejlouah
17-MayDenoising 2 + Rendering 1Denoising Deep Monte Carlo RenderingsXinyuan HuangIrene Baeza Rojo
Differentiable Monte Carlo Ray Tracing through Edge SamplingYuanhao HuangPrashanth Chandran
24-MayRendering 2Importance Sampling Techniques for Path Tracing in Participating MediaNicolas HafnerTobias Guenther
Residual Ratio Tracking for Estimating Attenuation in Participating MediaKarlis Martins BriedisIrene Baeza Rojo
31-MayVideo + VisualizationEpic Flow: Edge-Preserving Interpolation of Correspondences for Optical FlowAndreas RothPaulo Gotardo
Cores of Swirling Particle Motion in Unsteady FlowMichael BernasconiTobias Guenther

Further Papers

  • MonoPerfCap: Human Performance Capture from Monocular Video
  • Anatomically-Constrained Local Deformation Model for Monocular Face Capture
  • Practical Dynamic Facial Appearance Modeling and Acquisition
  • A Dual Light Stage
  • Polarization Imaging Reflectometry in the Wild
  • Extinction-Optimized Volume Illumination
  • SPNets: Differentiable Fluid Dynamics for Deep Neural Networks