Computer Graphics Laboratory ETH Zurich


Seminar 'Advanced Methods in Computer Graphics' - SS 20


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.


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


Virtual Seminar

The seminar takes place virtually using the video platform Zoom. Detailed information about the online session was sent to you once by e-mail. We will always use the same Zoom room. Note that there will be no physical session in the assigned class room. Presenters can contact us before the meeting to get a technical introduction to the video platform Zoom. There are a few important rules:

  • When attending a virtual meeting, log in with your real name.
  • Mute your microphone during the presentations.
  • Use a head set to avoid feedback loops.
We will monitor virtual attendence. 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.


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 O. Sorkine-Hornung
Assistants Dr. Vinicius C. Azevedo (, CNB G 102.1

Dr. Tobias Günther (, CNB G 102.1

Dr. Marco Manzi (, STD
Location Virtual Meeting, Fridays 13:00-15:00



Date Topic Paper Student Supervisor
06-MarNo session
13-MarNo session
20-MarMaterials 1 + Capture 1Displacement Interpolation using Lagrangian Mass TransportDaniel PeterTobias Guenther
MonoPerfCap: Human Performance Capture from Monocular VideoJohannes BaureithelMartin Guay
27-MarMaterials 2A Learned Shape-Adaptive Subsurface Scattering ModelAnil YarisXianyao Zhang
High-Contrast Computational Caustic DesignLuca Di BartolomeoMarios Papas
03-AprRenderingSelectively Metropolised Monte Carlo Light Transport SimulationRudolf VargaMarco Manzi
Importance Sampling Techniques for Path Tracing in Participating MediaRenato MentaTobias Guenther
10-AprNo sessionNo session
17-AprNo sessionNo session
24-AprCapture 2 + VideoPolarization Imaging Reflectometry in the WildAlessia PaccagnellaJeremy Riviere
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost VolumeJakob HeckelmannPaulo Gotardo
1-MayNo sessionNo session
08-MayAnimation 1Phase-functioned Neural Networks for Character ControlNiklaus HouskaDominik Borer
SMPL: A Skinned Multi-Person Linear ModelBörge ScheelDominik Borer
15-MayAnimation 2An Empirical Rig for Jaw AnimationAlexandre BinningerGaspard Zoss
A Deep Learning Approach for Generalized Speech AnimationBastian MorathPaulo Gotardo
22-MayNo sessionNo session
29-MayFluids 1A Stream Function Solver for Liquid SimulationsMaximilian WolfertzVinicius Azevedo
The Affine Particle-In-Cell MethodMelvin OttVinicius Azevedo

Further Papers

  • Residual Ratio Tracking for Estimating Attenuation in Participating Media
  • Adaptive Polynomial Rendering
  • Anatomically-Constrained Local Deformation Model for Monocular Face Capture
  • Practical Dynamic Facial Appearance Modeling and Acquisition
  • Noise Flow: Noise Modeling with Conditional Normalizing Flows
  • Photo Wake-Up: 3D Character Animation from a Single Photo
  • Deep Scattering: Rendering Atmospheric Clouds with Radiance-Predicting Neural Networks
  • Deferred Neural Rendering: Image Synthesis using Neural Textures
  • Mitsuba 2: A Retagetable Forward and Inverse Renderer
  • Denoising Deep Monte Carlo Renderings
  • Extinction-Optimized Volume Illumination
  • tempoGAN: A Temporally Coherent Volumetric GAN for Super-resolution Fluid Flow
  • Separable Subsurface Scattering