Learning Image Fractals Using Chaotic Differentiable Point Splatting
Loading...
Date
2025
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
Fractal geometry, defined by self-similar patterns across scales, is crucial for understanding natural structures. This work addresses the fractal inverse problem, which involves extracting fractal codes from images to explain these patterns and synthesize them at arbitrary finer scales. We introduce a novel algorithm that optimizes Iterated Function System parameters using a custom fractal generator combined with differentiable point splatting. By integrating both stochastic and gradient-based optimization techniques, our approach effectively navigates the complex energy landscapes typical of fractal inversion, ensuring robust performance and the ability to escape local minima. We demonstrate the method's effectiveness through comparisons with various fractal inversion techniques, highlighting its ability to recover high-quality fractal codes and perform extensive zoom-ins to reveal intricate patterns from just a single image.
Description
CCS Concepts: Computing methodologies → Point-based models; Rendering; Machine learning
@article{10.1111:cgf.70084,
journal = {Computer Graphics Forum},
title = {{Learning Image Fractals Using Chaotic Differentiable Point Splatting}},
author = {Djeacoumar, Adarsh and Mujkanovic, Felix and Seidel, Hans-Peter and Leimkühler, Thomas},
year = {2025},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.70084}
}