By-Example Synthesis of Vector Textures

2025-01-23

AI Summary

This work introduces the first end-to-end single-image vectorization method for texture synthesis, targeting the generation of structurally preserved, semantically layered, and infinitely scalable vector textures from a single raster input. The method comprises: (1) texton-based semantic segmentation and visual clustering; (2) texton relationship encoding via geometric neighborhood modeling; (3) hierarchical vector placement; and (4) data-driven background gradient field construction with color adaptation. Its core innovations are the texton neighborhood descriptor and gradient-guided color mapping, jointly ensuring structural, semantic, and stylistic consistency. Quantitative and qualitative evaluations demonstrate significant improvements over state-of-the-art approaches across multiple perceptual quality metrics. The output is compact SVG format, enabling high-fidelity scaling, localized editing, and cross-scale reuse—addressing key limitations of prior raster-based or non-semantic vectorization techniques.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Matrix & Tensor Methods

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text

Abstract

We propose a new method for synthesizing an arbitrarily sized novel vector texture given a single raster exemplar. Our method first segments the exemplar to extract the primary textons, and then clusters them based on visual similarity. We then compute a descriptor to capture each texton's neighborhood which contains the inter-category relationships that are used at synthesis time. Next, we use a simple procedure to both extract and place the secondary textons behind the primary polygons. Finally, our method constructs a gradient field for the background which is defined by a set of data points and colors. The color of the secondary polygons are also adjusted to better match the gradient field. To compare our work with other methods, we use a wide range of perceptual-based metrics.

Problem

• Vector Texture Generation
• Visual Consistency
• Pattern Distribution

Innovation

• Vector Texture Synthesis
• Single Sample Scalability
• Pattern Decomposition and Optimization