Marc Droske
Applied Mathematician (Dr. rer. nat., PhD)
- Distinguished Researcher at Wētā FX, New Zealand.
- Joined Weta in 2014. Head of Rendering Research: 2017-2023
- NVIDIA Advanced Rendering Center, Berlin, GPU-accelerated path tracing (iray), next-gen production rendering and geometry processing algorithms.
- Research mathematician at mental images
- Applied Mathematics at the University of Bonn and received my Diploma and PhD degree in the institute for Numerical Simulation (Bonn and Duisburg).
Dissertation On Variational Problems and Gradient Flows in Image Processing (PDF) (summa cum laude/with distinction) advised by Prof. Martin Rumpf.
- 2005-2006 PostDoc at UCLA Department of Mathematics, with Andrea Bertozzi and Stanley Osher.
Google Scholar ∙ ResearchGate ∙ LinkedIn ∙ IMDb ∙ Twitter
Interests
- production rendering, physically-based light transport, volume rendering
- impact and applicability of machine learning, DL on the above
- mathematical image processing, partial differential equations, calculus of variations, regularisation of gradient flows, inverse problems
- differential geometry, level set methods, geometry processing
Publications
Differentiating Variance for Variance-Aware Inverse Rendering
∙ ACM SIGGRAPH Asia 2024, Tokyo
A Multi-scale Yarn Appearance Model with Fiber Details
∙ Technical Report, Department of Computer Science, University of Manchester
Once-more Scattered Next-Event Estimation for Volume Rendering
∙ Eurographics Symposium on Rendering 2022
Road to New Lighting Workflows
∙ DigiPro '22: Proceedings of the 2022 Digital Production Symposium
Temporal Normal Distribution Functions
∙ Eurographics Symposium on Rendering 2020, DL-Track
Manuka: A Batch-Shading Architecture for Spectral Path Tracing in Movie Production
∙ Transactions on Graphics, 37(3), 2018
Manifold Next-Event Estimation
∙ Computer Graphics Forum - Proceedings of Eurographics Symposium on Rendering 2015
Hero Wavelength Spectral Sampling
∙ Computer Graphics Forum - Proceedings of Eurographics Symposium on Rendering 2014
Quasi-Monte Carlo Progressive Photon Mapping
∙ Monte Carlo and Quasi-Monte Carlo Methods 2010, Springer-Verlag, Berlin, 2012
Feature-Preserving Higher-Order Regularization
∙ SIAM Journal on Imaging Sciences, 2009
Mumford-Shah Based Registration: A Comparison of a level set and a Phase Field Approach
∙ Computing and Visualization in Science, 2009
Mathematical Methods in Time Series Analysis and Digital Image Processing
∙ Inverse Problems and Parameter Identification in Image Processing, 2008
Multi-Scale Joint Segmentation and Registration of Image Morphology
∙ IEEE Transactions on Pattern Recognition and Machine Intelligence, 29(12):2181–2194, 2007
A Phase Field Method for Joint Denoising, Edge Detection and Motion Estimation
∙ SIAM Journal on Applied Mathematics, 68(3):599–618, 2007
Mumford-Shah Model for One-to-One Edge Matching
∙ IEEE Transactions on Image Processing, 16(11):2720–2732, 2007
Computational methods for nonlinear image registration
∙ Mathematical Models for Registration and Applications to Medical Imaging, Mathematics in Industry, Volume 10. 2006
Cartoon Extraction Based on Anisotropic Image Classification
∙ Vision, Modeling and Visualization, 293–300. AKA Publishing, 2006
A Variational Framework for Joint Image Registration, Denoising and Edge Detection
∙ In Bildverarbeitung für die Medizin, 246–250. Springer, 2006
A Mumford-Shah level-set approach for geometric image registration
∙ SIAM Journal on Applied Mathematics, 66(6):2127–2148, 2006
An Image Processing Approach to Surface Matching
∙ Proc. of Eurographics Symposium on Geometry Processing, 207–216. 2005
Towards a Unified Framework for Scientific Computing
∙ R. Kornhuber, R. Hoppe, J. Périaux, O. Pironneau, O. Widlund, and J. Xu, editors, 15th International Conference on Domain Decomposition Methods, Vol. 40, Lecture notes in Computational Science and Engineering. 2004
A Variational Approach to Non-Rigid Morphological Registration
∙ SIAM Journal on Applied Mathematics, 64(2):668–687, 2004
A Level Set Formulation for Willmore Flow
∙ Interfaces and Free Boundaries, 6(3):361–378, 2004
Image Registration by a Regularized Gradient Flow - A Streaming Implementation in DX9 Graphics Hardware
∙ Computing, 73(4):373–389, 2004
Towards Fast Non–Rigid Registration
∙ Inverse Problems, Image Analysis and Medical Imaging, AMS Special Session Interaction of Inverse Problems and Image Analysis, volume 313, 67–84. AMS, 2002
A Multilevel Segmentation Method
∙ B. Girod, G. Greiner, H. Niemann, and H.-P. Seidel, editors, Vision, Modeling and Visualization, 327–336. 2000
Conceptual Free-Form Styling on the Responsive Workbench
∙ VRST Proceedings of the ACM symposium on Virtual reality software and technology, 2000
Miscellaneous
Path Tracing in Production: Part 1: Modern Path Tracing
∙ ACM SIGGRAPH 2019 Courses, SIGGRAPH '19, pages 19:1--19:113
Path Space Similarity Determined by Fourier Histogram Descriptors
∙ SIGGRAPH '14 ACM SIGGRAPH 2014 Talks
A Divide-and-Conquer Algorithm for Simultaneous Photon Map Queries
∙ Poster at High-Performance Graphics in Vancouver, 2011
On Variational Problems and Gradient Flows in Image Processing
∙ PhD Dissertation thesis, University of Duisburg, 2005
Patents
Divide-and-Conquer System, Method, and Computer Program Product for Providing Photon Mapping
∙ US Patent 8,847,957
System, Method, and Computer Program Product for Utilizing a Wavefront Path Tracer
∙ US Patent 9355492