Neural Contrast: Leveraging Generative Editing for Graphic Design Recommendations

TL;DR

This paper introduces a generative diffusion model-based method for graphic design that optimizes contrast and saliency, improving visual appeal without destructive alterations to background or text.

Contribution

It presents a novel generative editing technique leveraging diffusion models to enhance contrast and saliency in graphic design, surpassing traditional simple or destructive methods.

Findings

Effective contrast enhancement in composite images

Improved visibility of design assets

Non-destructive editing approach

Abstract

Creating visually appealing composites requires optimizing both text and background for compatibility. Previous methods have focused on simple design strategies, such as changing text color or adding background shapes for contrast. These approaches are often destructive, altering text color or partially obstructing the background image. Another method involves placing design elements in non-salient and contrasting regions, but this isn't always effective, especially with patterned backgrounds. To address these challenges, we propose a generative approach using a diffusion model. This method ensures the altered regions beneath design assets exhibit low saliency while enhancing contrast, thereby improving the visibility of the design asset.