Learning Image Fractals Using Chaotic Differentiable Point Splatting

Simple item page
dc.contributor.authorDjeacoumar, Adarshen_US
dc.contributor.authorMujkanovic, Felixen_US
dc.contributor.authorSeidel, Hans-Peteren_US
dc.contributor.authorLeimkühler, Thomasen_US
dc.contributor.editorBousseau, Adrienen_US
dc.contributor.editorDay, Angelaen_US
dc.date.accessioned2025-05-09T09:16:37Z
dc.date.available2025-05-09T09:16:37Z
dc.date.issued2025
dc.description.abstractFractal 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.en_US
dc.description.number2
dc.description.sectionheadersEclipsing the Ordinary in Visualization
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70084
dc.identifier.issn1467-8659
dc.identifier.pages14 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70084
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70084
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Point-based models; Rendering; Machine learning
dc.subjectComputing methodologies → Point
dc.subjectbased models
dc.subjectRendering
dc.subjectMachine learning
dc.titleLearning Image Fractals Using Chaotic Differentiable Point Splattingen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
cgf70084.pdf
Size:
24.51 MB
Format:
Adobe Portable Document Format
Download
Collections
EG 2025 - Full Papers - CGF 44-Issue 2
44-Issue 2