Differentiable Rendering Using Gaussian Mixtures
- Forschungsthema/Bereich
- Computer Graphics, Math, Computer Science
- Typ der Abschlussarbeit
- Bachelor / Master
- Startzeitpunkt
- -
- Bewerbungsschluss
- 31.03.2028
- Dauer der Arbeit
- 4 moths for a BSc and 6 months for an MSc
Beschreibung
Rendering synthesizes images from geometric descriptions of a scene. Traditional rendering pipelines operate on primitives such as triangles and surfaces, but their discrete visibility and rasterization operations often make differentiation with respect to scene parameters difficult. Gaussian Mixtures offer an alternative geometric representation, enabling smooth rendering operations and differentiable image synthesis. The project explores geometry-induced Gaussian representationsfor differentiable rendering. Starting from existing geometric models, such as triangle meshes or parametric surfaces, Gaussian components will be constructed and used for image synthesis. Possible directions include:• Constructing Gaussian components from geometric primitives.
• Investigating Gaussian means, covariances, and mixture weights.
• Developing differentiable projection, visibility, and compositing.
• Evaluating approximation quality, gradients, and rendering efficiency
Voraussetzung
- Voraussetzungen an Studierende
-
- • Firm grasp over Linear/Multilinear Algebra and Analysis
- • Good understanding of Probability and Statistics
- • Familiarity with Computer Graphics and geometric representations is advantageous
- • PyTorch or an equivalent NumPy-like framework
- • Some exposure to Differential Geometry is advantageous
- • Interest in numerical methods, mathematical modelling, and computer graphics
- Studiengangsbereiche
-
- Ingenieurwissenschaften
Elektrotechnik & Informationstechnik
Informatik
Remote Sensing and Geoinformatics
Electrical Engineering and Information Technology - Naturwissenschaften und Technik
Mathematik
Physik
Technomathematik
Computational and Data Sience
Physics
Wirtschaftsmathematik - Sonstiges z.B. Lehramt
Informatik
Mathematik
Physik - Wirtschafts- und Rechtswissenschaften
Wirtschaftsinformatik
- Ingenieurwissenschaften
Betreuung
- Titel, Vorname, Name
- Ali Darijani
- Organisationseinheit
- Fraunhofer IOSB/KIT CS
- E-Mail Adresse
- ali.darijani@iosb.fraunhofer.de
- Link zur eigenen Homepage/Personenseite
- Website
Bewerbung per E-Mail
- Bewerbungsunterlagen
-
- Lebenslauf
- Notenauszug
- Whatever that you like me to see!
E-Mail Adresse für die Bewerbung
Senden Sie die oben genannten Bewerbungsunterlagen bitte per Mail an ali.darijani@iosb.fraunhofer.de
Zurück