A new Image Similarity Metric for a Perceptual and Transparent Geometric and Chromatic Assessment

TL;DR

This paper introduces a new perceptual image similarity metric that combines texture and color dissimilarity measures, outperforming existing metrics especially with shape distortions, and offers visual explanations for its assessments.

Contribution

The paper presents a novel perceptual image similarity metric that integrates Earth Mover's Distance for textures and Oklab color space for chromatic differences, with visual explanation capabilities.

Findings

Outperforms state-of-the-art metrics on complex distortions

Better at evaluating shape and texture distortions

Provides visual explanations for similarity scores

Abstract

In the literature, several studies have shown that state-of-the-art image similarity metrics are not perceptual metrics; moreover, they have difficulty evaluating images, especially when texture distortion is also present. In this work, we propose a new perceptual metric composed of two terms. The first term evaluates the dissimilarity between the textures of two images using Earth Mover's Distance. The second term evaluates the chromatic dissimilarity between two images in the Oklab perceptual color space. We evaluated the performance of our metric on a non-traditional dataset, called Berkeley-Adobe Perceptual Patch Similarity, which contains a wide range of complex distortions in shapes and colors. We have shown that our metric outperforms the state of the art, especially when images contain shape distortions, confirming also its greater perceptiveness. Furthermore, although deep black-box metrics could be very accurate, they only provide similarity scores between two images, without explaining their main differences and similarities. Our metric, on the other hand, provides visual explanations to support the calculated score, making the similarity assessment transparent and justified.