Realistic Saliency Guided Image Enhancement

TL;DR

This paper introduces a realism loss for saliency-guided image enhancement that effectively reduces distractors and emphasizes subjects while maintaining high photo realism, outperforming existing methods.

Contribution

It proposes a novel realism loss function that improves saliency-guided image enhancement, balancing attention manipulation with realistic results, validated by professional photographer evaluations.

Findings

Achieves better realism and effectiveness than recent approaches.

Requires less memory and runtime than competing methods.

Validated by professional photographers' assessments.

Abstract

Common editing operations performed by professional photographers include the cleanup operations: de-emphasizing distracting elements and enhancing subjects. These edits are challenging, requiring a delicate balance between manipulating the viewer's attention while maintaining photo realism. While recent approaches can boast successful examples of attention attenuation or amplification, most of them also suffer from frequent unrealistic edits. We propose a realism loss for saliency-guided image enhancement to maintain high realism across varying image types, while attenuating distractors and amplifying objects of interest. Evaluations with professional photographers confirm that we achieve the dual objective of realism and effectiveness, and outperform the recent approaches on their own datasets, while requiring a smaller memory footprint and runtime. We thus offer a viable solution for automating image enhancement and photo cleanup operations.