Point Pattern Synthesis via Irregular Convolution

dc.contributor.authorTu, Peihanen_US
dc.contributor.authorLischinski, Danien_US
dc.contributor.authorHuang, Huien_US
dc.contributor.editorBommes, David and Huang, Huien_US
dc.date.accessioned2019-07-11T06:19:29Z
dc.date.available2019-07-11T06:19:29Z
dc.date.issued2019
dc.description.abstractPoint pattern synthesis is a fundamental tool with various applications in computer graphics. To synthesize a point pattern, some techniques have taken an example-based approach, where the user provides a small exemplar of the target pattern. However, it remains challenging to synthesize patterns that faithfully capture the structures in the given exemplar. In this paper, we present a new example-based point pattern synthesis method that preserves both local and non-local structures present in the exemplar. Our method leverages recent neural texture synthesis techniques that have proven effective in synthesizing structured textures. The network that we present is end-to-end. It utilizes an irregular convolution layer, which converts a point pattern into a gridded feature map, to directly optimize point coordinates. The synthesis is then performed by matching inter- and intra-correlations of the responses produced by subsequent convolution layers. We demonstrate that our point pattern synthesis qualitatively outperforms state-of-the-art methods on challenging structured patterns, and enables various graphical applications, such as object placement in natural scenes, creative element patterns or realistic urban layouts in a 3D virtual environment.en_US
dc.description.number5
dc.description.sectionheadersSynthesis and Learning
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume38
dc.identifier.doi10.1111/cgf.13793
dc.identifier.issn1467-8659
dc.identifier.pages109-122
dc.identifier.urihttps://doi.org/10.1111/cgf.13793
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13793
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.titlePoint Pattern Synthesis via Irregular Convolutionen_US
Files
Collections