Predicting Visual Importance Across Graphic Design Types

TL;DR

This paper presents UMSI, a unified deep learning model that predicts visual importance across various graphic design types and natural images, supported by a new dataset and practical applications.

Contribution

A novel deep learning model trained on diverse design classes with an automatic classification module, enabling effective importance prediction without prior input labeling.

Findings

UMSI outperforms specialized models in importance prediction accuracy.

Introduces Imp1k, a comprehensive dataset of annotated design importance.

Demonstrates practical design tools utilizing importance prediction.

Abstract

This paper introduces a Unified Model of Saliency and Importance (UMSI), which learns to predict visual importance in input graphic designs, and saliency in natural images, along with a new dataset and applications. Previous methods for predicting saliency or visual importance are trained individually on specialized datasets, making them limited in application and leading to poor generalization on novel image classes, while requiring a user to know which model to apply to which input. UMSI is a deep learning-based model simultaneously trained on images from different design classes, including posters, infographics, mobile UIs, as well as natural images, and includes an automatic classification module to classify the input. This allows the model to work more effectively without requiring a user to label the input. We also introduce Imp1k, a new dataset of designs annotated with importance information. We demonstrate two new design interfaces that use importance prediction, including a tool for adjusting the relative importance of design elements, and a tool for reflowing designs to new aspect ratios while preserving visual importance. The model, code, and importance dataset are available at https://predimportance.mit.edu .