Neural Image Abstraction Using Long Smoothing B-Splines

TL;DR

This paper introduces a method that integrates smoothing B-splines into differentiable vector graphics pipelines, enabling the creation of smooth, stylized vector graphics with controllable fidelity and stylization features.

Contribution

It presents a novel integration of smoothing B-splines into DiffVG, allowing for flexible, stylized vector graphic generation with derivative-based control over smoothness and fidelity.

Findings

Demonstrates stylized space-filling path generation

Enables stroke-based image abstraction

Supports stylized text generation

Abstract

We integrate smoothing B-splines into a standard differentiable vector graphics (DiffVG) pipeline through linear mapping, and show how this can be used to generate smooth and arbitrarily long paths within image-based deep learning systems. We take advantage of derivative-based smoothing costs for parametric control of fidelity vs. simplicity tradeoffs, while also enabling stylization control in geometric and image spaces. The proposed pipeline is compatible with recent vector graphics generation and vectorization methods. We demonstrate the versatility of our approach with four applications aimed at the generation of stylized vector graphics: stylized space-filling path generation, stroke-based image abstraction, closed-area image abstraction, and stylized text generation.