Controlling Geometric Abstraction and Texture for Artistic Images

TL;DR

This paper introduces a holistic, interactive method for artistic image stylization that independently controls shape, texture, and color, enabling precise editing and style transfer through a parametric, differentiable pipeline.

Contribution

It presents a novel approach that spatially decomposes images into shape and texture parameters, allowing independent control and real-time style transfer, unlike previous entangled stylization methods.

Findings

Enables independent editing of shape and texture in artistic images.

Supports real-time style transfer using reference images and text prompts.

Provides a differentiable pipeline for interactive and automated stylization.

Abstract

We present a novel method for the interactive control of geometric abstraction and texture in artistic images. Previous example-based stylization methods often entangle shape, texture, and color, while generative methods for image synthesis generally either make assumptions about the input image, such as only allowing faces or do not offer precise editing controls. By contrast, our holistic approach spatially decomposes the input into shapes and a parametric representation of high-frequency details comprising the image's texture, thus enabling independent control of color and texture. Each parameter in this representation controls painterly attributes of a pipeline of differentiable stylization filters. The proposed decoupling of shape and texture enables various options for stylistic editing, including interactive global and local adjustments of shape, stroke, and painterly attributes such as surface relief and contours. Additionally, we demonstrate optimization-based texture style-transfer in the parametric space using reference images and text prompts, as well as the training of single- and arbitrary style parameter prediction networks for real-time texture decomposition.