Sebastian Weiss
Personal Homepage
Email: contact@sebastian-weiss.eu
About me
I’m an Assistant Research Scientist with the VFX group at DisneyResearch|Studios. My main research areas are computer graphics and machine learning, with a focus on appearance modeling, texture synthesis, and super-resolution.
I received my BSc, MSc degree and my Ph.D. degree in Informatics from the Technical University of Munich (TUM) under the supervision of Nils Thuerey (BSc, MSc), Daniel Cremers (MSc) and Rüdiger Westermann (Ph.D.). Prior to joining Disney Research, my main focus was in deep learning and high-performance GPU programming for scientific volume visualization.
Publications
Sebastian Weiss, Mustafa Işık, Justus Thies, Rüdiger Westermann
TVCG 2020
[PDF] [Preprint] [BIB] [Source Code]
Volumetric Isosurface Rendering with Deep Learning-Based Super-Resolution
Sebastian Weiss, Mengyu Chu, Nils Thuerey, Rüdiger Westermann
TVCG 2019
[PDF] [Preprint] [BIB] [Source Code] [Video]
Correspondence-Free Material Reconstruction using Sparse Surface Constraints
Sebastian Weiss, Robert Maier, Daniel Cremers, Rüdiger Westermann, Nils Thuerey
CVPR 2020
[PDF] [Preprint] [BIB] [Source Code] [Video]
Triplanar Displacement Mapping for Terrain Rendering
Sebastian Weiss, Florian Bayer, Rüdiger Westermann
Eurographics 2020
[PDF] [Preprint] [BIB] [Source Code]
Teaching
Summer Term 2019 - Seminar: How to make A PIXAR movie
Summer Term 2019 - exercises for Algorithms and Datastructures for Electrical Engineering
Winter Term 2019/20 - Seminar: Data Visualization
Summer Term 2020 - Seminar: Data Visualization
Summer Term 2020 - exercises for Realtime Computer Graphics
Supervised Theses, see https://www.in.tum.de/cg/people/weiss/ for a full list
2019: 2 bachelor, 1 master theses
2020: 3 bachelor, 3 master theses
Talks
2020
June 17, 2020, Correspondence-Free Material Reconstruction using Sparse Surface Constraints, CVPR, online
October 29, 2020, Volumetric Isosurface Rendering with Deep Learning-Based Super-Resolution, IEEE VIS, online
2016
October 26, 2016, SciVis Context on Visualizing Viscous Fingers, IEEE Vis, Baltimore, USA
Tech Reports / Other Resources
PyTorch - CUDA - C++ Interop (presentation held in January 2020)
[Slides] [Source Code]Inverse Volume Rendering + Introduction to Automatic Differentiation (presentation held in November 2020)
[Slides]Volume Rendering Integral: Derivation of the Front-to-back Algorithm (tech report, December 2020)
[PDF]