Point Pattern Synthesis via Irregular Convolution

Abstract

Point 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.