Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Exploration of Alternative Image Representation Using Signed Distance Functions

Olejnik, Jakub LU (2023) MAMM15 20231
Department of Design Sciences
Abstract
This project leverages the core concepts of differentiable rendering to find alternative representation of images using geometric primitives rendered with Signed Distance Functions. By utilising gradient-descent-based methods it is possible to find optimal parameters of rendered primitives to create high-quality reconstruction. Moreover, this research serves as a foundation for extending the principles and methodologies explored to 2D space. While the project primarily focuses on 2D image representation, the insights gained can be applied to similar tasks in the field of 3D rendering.
Popular Abstract
This project leverages the core concepts of differentiable rendering to find alternative representation of images using geometric primitives rendered with Signed Distance Functions. By utilising machine learning it is possible to find optimal parameters of rendered primitives to create high-quality reconstructions.
Please use this url to cite or link to this publication:
author
Olejnik, Jakub LU
supervisor
organization
course
MAMM15 20231
year
type
H2 - Master's Degree (Two Years)
subject
keywords
computer graphics, SDF-based rendering, machine learning
language
English
id
9129143
date added to LUP
2023-06-26 10:42:28
date last changed
2023-06-26 10:42:28
@misc{9129143,
  abstract     = {{This project leverages the core concepts of differentiable rendering to find alternative representation of images using geometric primitives rendered with Signed Distance Functions. By utilising gradient-descent-based methods it is possible to find optimal parameters of rendered primitives to create high-quality reconstruction. Moreover, this research serves as a foundation for extending the principles and methodologies explored to 2D space. While the project primarily focuses on 2D image representation, the insights gained can be applied to similar tasks in the field of 3D rendering.}},
  author       = {{Olejnik, Jakub}},
  language     = {{eng}},
  note         = {{Student Paper}},
  title        = {{Exploration of Alternative Image Representation Using Signed Distance Functions}},
  year         = {{2023}},
}