Look here! A parametric learning based approach to redirect visual attention

TL;DR

This paper introduces GazeShiftNet, a parametric learning method that subtly edits images to effectively redirect viewer attention while maintaining realism, outperforming prior techniques in preserving semantics and avoiding artifacts.

Contribution

The paper presents a novel global parametric approach for attention shifting that preserves image semantics and enables real-time, customizable edits suitable for images and videos.

Findings

Outperforms prior state-of-the-art in attention shifting

Maintains image realism and semantics

Enables real-time, customizable edits

Abstract

Across photography, marketing, and website design, being able to direct the viewer's attention is a powerful tool. Motivated by professional workflows, we introduce an automatic method to make an image region more attention-capturing via subtle image edits that maintain realism and fidelity to the original. From an input image and a user-provided mask, our GazeShiftNet model predicts a distinct set of global parametric transformations to be applied to the foreground and background image regions separately. We present the results of quantitative and qualitative experiments that demonstrate improvements over prior state-of-the-art. In contrast to existing attention shifting algorithms, our global parametric approach better preserves image semantics and avoids typical generative artifacts. Our edits enable inference at interactive rates on any image size, and easily generalize to videos. Extensions of our model allow for multi-style edits and the ability to both increase and attenuate attention in an image region. Furthermore, users can customize the edited images by dialing the edits up or down via interpolations in parameter space. This paper presents a practical tool that can simplify future image editing pipelines.