Point-Pattern Synthesis using Gabor and Random Filters

Xingchang Huang1, Pooran Memari2, Hans-Peter Seidel1, Gurprit Singh1
1Max Planck Institute for Informatics, Saarbrücken, 2 CNRS, LIX, Ecole Polytechnique, Paris, France
EGSR 2022 / Computer Graphics Forum, Volume 41 issue 6, July 2022
Our method takes simply a point set (with positions, classes, attributes) as input and applies continuous Gabor transform to extract features. We then use these Gabor features to perform pattern expansion for a large canvas. We show synthesis results of a 2-class point pattern in (a), and a 4-class point pattern with depth and scale as attributes in (b).


Point pattern synthesis requires capturing both local and non-local correlations from a given exemplar. Recent works employ deep hierarchical representations from VGG-19 convolutional network to capture the features for both point-pattern and texture synthesis. In this work, we develop a simplified optimization pipeline that uses more traditional Gabor transform-based features. These features when convolved with simple random filters gives highly expressive feature maps. The resulting framework requires significantly less feature maps compared to VGG-19-based methods, better captures both the local and non-local structures, does not require any specific data set training and can easily extend to handle multi-class and multi-attribute point patterns, e.g., disk and other element distributions. To validate our pipeline, we perform qualitative and quantitative analysis on a large variety of point patterns to demonstrate the effectiveness of our approach. Finally, to better understand the impact of random filters, we include a spectral analysis using filters with different frequency bandwidths.


Paper (author version)
Supplemental document
Source code


We would like to thank the anonymous reviewers for their valuable comments and Pierre Ecormier-Nocca for helping with object placement in Blender. We would also like to thank Reddy and colleagues [RGF*20] for making their source code and data publicly available. Renderings shown in the results use free models from Turbosquid under the "Editorial Use" license.

Copyright Disclaimer

The Author(s). This is the author's version of the work. It is posted here by permission of The Eurographics Association for your personal use. Not for redistribution. The definitive version is available at diglib.eg.org.

Imprint / Data Protection