A Procedural Texture Generation Framework Based on Semantic Descriptions

TL;DR

This paper presents a framework that enables naive users to generate procedural textures based on semantic descriptions by mapping these descriptions to procedural models through a learned semantic space.

Contribution

It introduces a novel semantic-based procedural texture generation framework with a learned mapping from semantic attributes to texture models.

Findings

The framework effectively generates textures matching semantic descriptions.

A semantic space enables separation and retrieval of appropriate procedural models.

Generated textures closely align with input semantic attributes.

Abstract

Procedural textures are normally generated from mathematical models with parameters carefully selected by experienced users. However, for naive users, the intuitive way to obtain a desired texture is to provide semantic descriptions such as "regular," "lacelike," and "repetitive" and then a procedural model with proper parameters will be automatically suggested to generate the corresponding textures. By contrast, it is less practical for users to learn mathematical models and tune parameters based on multiple examinations of large numbers of generated textures. In this study, we propose a novel framework that generates procedural textures according to user-defined semantic descriptions, and we establish a mapping between procedural models and semantic texture descriptions. First, based on a vocabulary of semantic attributes collected from psychophysical experiments, a multi-label learning method is employed to annotate a large number of textures with semantic attributes to form a semantic procedural texture dataset. Then, we derive a low dimensional semantic space in which the semantic descriptions can be separated from one other. Finally, given a set of semantic descriptions, the diverse properties of the samples in the semantic space can lead the framework to find an appropriate generation model that uses appropriate parameters to produce a desired texture. The experimental results show that the proposed framework is effective and that the generated textures closely correlate with the input semantic descriptions.