Ritschel, Tobias

Tobias Ritschel, Dr.-Ing.

Professor of Computer Graphics
University College London


Research Interests

Interactive Global Illumination
How can graphics hardware (GPUs) be used to reproduce advanced visual phenomena such as soft shadows, indirect shadows, soft reflections, caustics or volumetric light in a perceptually plausible way?
Perceptual Graphics
How are colors, shapes, or spatial layout perceived by a human observer? How can this understanding be used to predict and consequently improve the way a humans and machines interact?
Non-physical Graphics
While physical laws define how to do render shadows or reflections "right", how to properly project a 3D scene onto a 2D image or how to deform a shape in a physical way, they sometimes are to restrictive. How can we go beyond physical laws in an appropriate way, such that a machine offers new expressive posibilities to an artist?
Data-driven Graphics
Given the vast amount of information in user-generated content online, how can classic computer graphics techniques such as rendering or shape modelling benefit from them and for which new application will they allow?


My office hours are Monday, 10:00--11:00. Contact me via email first.

1T 2020 Lecture Mitra/Ritschel Deep Learning for Visual Computing (COMP0169)
1T 2020 Lecture Ritschel Computer Graphics (COMP0027)
1T 2019 Lecture Ritschel Computer Graphics (COMP0027)
1T 2018 Lecture Ritschel Computer Graphics (COMP3080/GV10)
1T 2018 Lecture Ritschel/Steed Virtual Environments (COMPM076/GV07)
1T 2017 Lecture Ritschel/Steed Computer Graphics (COMP3080/GV10)
1T/2T 2017 Project Ritschel Individual Project (COMPGV99)
1T 2016 Lecture Ritschel/Steed Computer Graphics (COMP3080/GV10)
1T 2015 Lecture Steed/Ritschel Computer Graphics (COMP3080/GV10)
SS 2015 Lecture Ritschel Interactive Graphics using OpenGL
Lecture Slusallek/Myszkowski Realistic Image Synthesis, (13th and 16th of July)
WS 2014 Lecture Myszkowski/Ritschel/Didyk Perception for Computer Graphics
Praktikum Ritschel 3D-Rekonstruktion "Alte Schmelz", St. Ingbert
SS 2014 Seminar Ritschel Interactive Global Illumination
WS 2013 Seminar Ritschel Creative Computing
Lecture Vangorp/Myszkowski/Ritschel Perception for Computer Graphics
Praktikum Ritschel 3D-Rekonstruktion "Alte Schmelz", St. Ingbert ("aktueller bericht", SR Fernsehen, 15.04.2014.)
WS 2012 Seminar Ritschel/Reinhard/Myszkowski Applied Perception
Seminar Ihrke/Ritschel/Fritz Parallel Visual Computing
SS 2012 Seminar Thormählen/Ritschel Visual Computing Techniques for Efficient Content Production (Saarland University)
Lecture Slusallek/Myszkowski Realistic Image Synthesis, (11th and 16th of July)


Philipp HenzlerPhD student
Michael FischerPhD student
David GriffithsPhD student (with J Boehm)
David WaltonPostdoc (with A Steed)
Rafael Kuffner dos AnjosPostdoc (with A Steed)


X-Fields: Implicit Neural View-, Light- and Time-Image Interpolation
M Bemana, K Myszkowski, H-P Seidel, T Ritschel
ACM Trans. Graph. (Proc. SIGGRAPH Asia) 39(5) (Conditionally accepted)

Learning a Neural 3D Texture Space from 2D Exemplars
P Henzler, N Mitra, T Ritschel
Proc. CVPR

Finding Your (3D) Center: 3D Object Detection Using a Learned Loss
D Griffiths, J Boehm, T Ritschel
Proc. ECVV

Intrinsic-Extrinsic Convolution and Pooling for Scalable Deep Protein Analysis
P Hermosilla, M Schäfer, M Lang, G Fackelmann, P P Vázquez, B Kozlíková, M Krone, T Ritschel, T Ropinski


Perceptual Rasterization for Head-mounted Display Image Synthesis
S Friston, T Ritschel, A Steed
ACM Trans. Graph. (Proc. SIGGRAPH) 38(3)

Deep Point Correlation Design
T Leimkühler, G Singh, H-P Seidel, K Myszkowski, T Ritschel
ACM Trans. Graph. (Proc. SIGGRAPH Asia) 38(5)

Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning
P Hermosilla, T Ritschel, T Ropinski
Proc. ICCV

Deep Appearance Maps
M Maximov, L Leal-Taixé, M Fritz, T Ritschel
Proc. ICCV

Escaping Plato's Cave using Adversarial Training: 3D Shape From Unstructured 2D Image Collections
P Henzler, NJ Mitra, T Ritschel
Proc . ICCV

Learning on the Edge: Explicit Boundary Handling in CNNs
C Innamorati, T Ritschel, T Weyrich, NJ Mitra
Int J Computer Vision (to appear)

Deep-learning the Latent Space of Light Transport
P Hermosilla, S Maisch, T Ritschel, T Ropinski
Comp. Graph. Forum (Proc. EGSR) 38(5)

Learning to Predict Image-based Rendering Artifacts in Respect to a Hidden Reference Image
M Bemana, J Keinert, K Myszkowski, M Bätz, M Ziegler, H-P Seidel, T Ritschel
Comp. Graph. Forum 38 (?) (Proc. Pacific Graphics)

Distortion-free Displacement Mapping
T Zirr, T Ritschel
Comp. Graph. Forum (Proc. HPG) 38(4)


Laplacian Kernel Splatting for Efficient Depth-of-field and Motion Blur Synthesis or Reconstruction
T Leimkühler, H-P Seidel, T Ritschel
ACM Trans. Graph. (Proc. SIGGRAPH) 37(3)

Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds
P Hermosilla, T Ritschel, P-P Vázquez, A Vinacua, T Ropinski
ACM Trans Graph (Proc. SIGRAPH Asia) 37(5)

Single-image Tomography: 3D Volumes from 2D X-Rays
P Henzler, T Ritschel, P Rasche, T Ropinski
Comp. Graph. Forum (Proc. Eurographics) 37(3)

Learning on the Edge: Explicit Boundary Handling in CNNs
C Innamorati, T Ritschel, T Weyrich, NJ Mitra
Proc. BMVC (Selected for oral presentation)

Joint Material and Illumination Estimation from Photo Sets in the Wild
Proc. 3DV (Selected for oral presentation)

End-to-end Sampling Patterns
T Leimkühler, G Singh, H-P Seidel, K Myszkowski, T Ritschel
arXiV abs/1806.6710
arXiV abs/1806.05385
arXiV abs/1804.00863
arXiV abs/1812.02552
arXiV abs/1811.04756
arXiV abs/1811.11606


Reflectance and Natural Illumination from Single-Material Specular Objects Using Deep Learning

Perceptual real-time 2D-to-3D conversion using cue fusion

Practical Capture and Reproduction of Phosphorescent Appearance

Texture Stationarization: Turning Photos into Tileable Textures

Minimal Warping: Planning Incremental Novel-view Synthesis

Deep Shading: Convolutional Neural Networks for Screen Space Shading

Decomposing Single Images for Layered Photo Retouching
WARNING: No decoration for innamorati2017decomposingretouching

What Is Around the Camera?


Motion Parallax in Stereo 3D: Model and Applications

Scalable Inside-Out Image-Based Rendering

Novel Views of Objects from a Single Image

Deep Reflectance maps
Proc. CVPR
WARNING: Missing volume

Proxy-guided Image-based Rendering for Mobile Devices

Efficient Multi-image Correspondences for On-line Light Field Video Processing
L Dabala, M Ziegler, P Didyk, F Zilly, J Keinert, K Myszkowski, H-P Seidel, P Rokita, T Ritschel
Comput. Graph. Forum 35(7) (Proc. Pacific Graphics)

Transformation-aware perceptual image metric
WARNING: No decoration for kellnhofer2016transformationawaremetric

Perceptual real-time 2D-to-3D conversion using cue fusion

Animated 3D Creatures from Single-view video by Skeletal Sketching

Real-time Novel-view Synthesis for Volume Rendering Using a Piecewise-analytic Representation

Deep Shading: Convolutional Neural Networks for Screen-Space Shading
WARNING: Missing both issue and number

DeLight-Net: Decomposing Reflectance Maps into Specular Materials and Natural Illumination
WARNING: Missing both issue and number

Natural Illumination from Multiple Materials Using Deep Learning
WARNING: Missing both issue and number
WARNING: No decoration for georgoulis2016naturallearning

Using Simulated Visual Illusions and Perceptual Anomalies to Convey Dynamic Range


Vision, Modeling & Visualization, VMV 2015, Aachen, Germany, October 7-10, 2015

Eurographics 2015 - Short Papers, Zurich, Switzerland, May 4-8, 2015

Data-Driven Color Manifolds

Deep Reflectance Maps
Proc. CVPR
WARNING: Missing volume

Guiding Image Manipulations using Shape-appearance Subspaces from Co-alignment of Image Collections

Modeling Luminance Perception at Absolute Threshold

Purkinje Images: Conveying Different Content for Different Luminance Adaptations in a Single Image

Projective Blue-Noise Sampling
Computer Graphics Forum
WARNING: Missing both issue and number
WARNING: No decoration for reinert2015projectivesampling

What makes 2D-to-3D stereo conversion perceptually plausible?

The Bounced Z-buffer for Indirect Visibility

What Is Holding Back Convnets for Detection?

A transformation-aware perceptual image metric
WARNING: No decoration for kellnhofer2015ametric

3D Object Class Detection in the Wild
WARNING: Missing both issue and number


On-line Learning of Parametric Mixture Models for Light Transport Simulation

Manipulating refractive and reflective binocular disparity

Spectral Ray Differentials

Principal-Ordinates Propagation for real-time rendering of participating media
WARNING: Missing both issue and number

Stereo Day-for-Night: Retargeting Disparity for Scotopic Vision
WARNING: No decoration for kellnhofer2014stereovision

Image-based Synthesis and Re-Synthesis of Viewpoints Guided by 3D Models

Interactive light scattering with principal-ordinate propagation

Deep screen space

Deep Screen Space for Indirect Lighting of Volumes

Interactive Appearance Editing in RGB-D Images

Real-time Reflective and Refractive Novel-view Synthesis

Progressive Spectral Ray Differentials

Improving Perception of Binocular Stereo Motion on 3D Display Devices
WARNING: No decoration for kellnhofer2014improvingdevices


Interactive By-example Design of Artistic Packing Layouts

Material Editing in Complex Scenes by Surface Light Field Manipulation and Reflectance Optimization

Optimizing Disparity for Motion in Depth

Real-Time Screen-Space Scattering in Homogeneous Environments

Generating Realistic Camera Shake for Virtual Scenes
J Virtual Reality and Broadcast
WARNING: Missing both issue and number


Highlight Microdisparity for Improved Gloss Depiction

A Luminance-Contrast-Aware Disparity Model and Applications

Material Memex: Automatic Material Suggestions for 3D Objects
WARNING: No decoration for jain2012materialobjects

Exploring Shape Variations by 3D-Model Decomposition and Part-based Recombination

3D Material Style Transfer

A Computational Model of Afterimages

Pre-convolved Radiance Caching

Homunculus Warping: Conveying importance using self-intersection-free non-homogeneous mesh deformation

The State of the Art in Interactive Global Illumination

Interactive cloud rendering using temporally coherent photon mapping

Mapping Images to Target Devices: Spatial, Temporal, Stereo, Tone, and Color

Apparent Stereo: The Cornsweet Illusion Can Enhance Perceived Depth
WARNING: No decoration for didyk2012apparentdepth

Virtual passepartouts


A Perceptual Model for Disparity

Edge-Aware Color Appearance

Computer-Suggested Facial Makeup

ManyLoDs: Parallel Many-View Level-of-Detail Selection for Real-Time Global Illumination
WARNING: No decoration for hollaender2011manylodsillumination

Making Imperfect Shadow Maps View-Adaptive: High-Quality Global Illumination in Large Dynamic Scenes

Bent Normals and Cones in Screen-space

Separable Approximation of Ambient Occlusion

Apparent resolution enhancement for animations


Apparent Display Resolution Enhancement for Moving Images

Interactive on-surface signal deformation

Perceptually-motivated Real-time Temporal Upsampling of 3D Content for High-refresh-rate Displays

Adaptive Image-space Stereo View Synthesis


Interactive Reflection Editing

Micro-Rendering for Scalable, Parallel Final Gathering

Temporal Glare: Real-Time Dynamic Simulation of the Scattering in the Human Eye

Perceptual Influence of Approximate Visibility in Indirect Illumination

Approximating dynamic global illumination in image space

Real-time indirect illumination with clustered visibility

A perceptual evaluation of 3D unsharp masking


3D unsharp masking for scene coherent enhancement

Imperfect shadow maps for efficient computation of indirect illumination

Interactive Global Illumination Based on Coherent Surface Shadow Maps


Fast GPU-based Visibility Computation for Natural Illumination of Volume Data Sets

Interactive Illumination with Coherent Shadow Maps


Multiresolution GPU Mesh Painting

Recent Positions


Previous Group Members

Daniel ScherzerPost doc (Now Hochschule Ravensburg-Weingarten)
Carlo InnamoratiPhD student (Inverse Graphics via Simulation-driven Learning)
Thomas LeimkühlerPhD student (Artificial Intelligence for Novel-view Synthesis | Now at INRIA Sophia-Antipolis)
Oliver NalbachPhD student (Smart Screen Space)
Chuong NguyenPhD student (Advanced Perceptual Design and Depiction of Materials | Now Apple Inc.)
Oskar ElekPhD student (Efficient Physically-based Rendering | Now Charles U Prague)
Bernhard ReinertPhD student (Interactive, Example-driven Synthesis and Manipulation of Visual Media | Now Google)
Konstantinos RematasVisiting PhD student
Pablo Bauszat,Visiting PhD student
Jiri VorbaVisiting PhD student
Ondrej Karlik,Visiting PhD student
Łukasz DąbałaVisiting Phd student
Sukumar SrikanthMaster Student
Andreas ZinsBachelor student
Phlipp HenzlerIntern
Adam LaskowksiIntern
Jozef HladkyIntern
Fabian RoschyHiWi
Marc HabermannHiWi, Bachelor student
Tobias BertelHiWi, Master student
Elena ArabadzhiyskaHiWi, Master student
Dushyant MehtaHiWi
Adam HankaMaster student
Fanyu YeHiWi
Benjamin SommerHiWi