Point-Pattern Synthesis using Gabor and Random Filters

dc.contributor.authorHuang, Xingchangen_US
dc.contributor.authorMemari, Pooranen_US
dc.contributor.authorSeidel, Hans-Peteren_US
dc.contributor.authorSingh, Gurpriten_US
dc.contributor.editorGhosh, Abhijeeten_US
dc.contributor.editorWei, Li-Yien_US
dc.date.accessioned2022-07-01T15:37:21Z
dc.date.available2022-07-01T15:37:21Z
dc.date.issued2022
dc.description.abstractPoint pattern synthesis requires capturing both local and non-local correlations from a given exemplar. Recent works employ deep hierarchical representations from VGG-19 [SZ15] 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 [TLH19; RGF*20], 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.en_US
dc.description.number4
dc.description.sectionheadersPatterns and Noises
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume41
dc.identifier.doi10.1111/cgf.14596
dc.identifier.issn1467-8659
dc.identifier.pages169-179
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14596
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14596
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 pattern synthesis; Point-based texture synthesis
dc.subjectComputing methodologies
dc.subjectPoint pattern synthesis
dc.subjectPoint based texture synthesis
dc.titlePoint-Pattern Synthesis using Gabor and Random Filtersen_US
Files
Original bundle
Now showing 1 - 3 of 3
Loading...
Thumbnail Image
Name:
v41i4pp169-179.pdf
Size:
28.03 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
supplemental_materials.zip
Size:
50.09 MB
Format:
Zip file
Loading...
Thumbnail Image
Name:
cgf14596-v41i4pp169-179.pdf
Size:
28.27 MB
Format:
Adobe Portable Document Format
Description:
ProjektDeal version
Collections