SAMScore: A Content Structural Similarity Metric for Image Translation Evaluation

TL;DR

SAMScore is a novel content structural similarity metric leveraging the Segment Anything Model to accurately evaluate the faithfulness of image translation models across various tasks.

Contribution

The paper introduces SAMScore, a new high-accuracy content structural similarity metric for image translation evaluation, outperforming existing metrics.

Findings

SAMScore outperforms all other metrics on 19 image translation tasks.

It effectively measures content faithfulness beyond pixel-wise similarity.

SAMScore is applicable to diverse image translation applications.

Abstract

Image translation has wide applications, such as style transfer and modality conversion, usually aiming to generate images having both high degrees of realism and faithfulness. These problems remain difficult, especially when it is important to preserve content structures. Traditional image-level similarity metrics are of limited use, since the content structures of an image are high-level, and not strongly governed by pixel-wise faithfulness to an original image. To fill this gap, we introduce SAMScore, a generic content structural similarity metric for evaluating the faithfulness of image translation models. SAMScore is based on the recent high-performance Segment Anything Model (SAM), which allows content similarity comparisons with standout accuracy. We applied SAMScore on 19 image translation tasks, and found that it is able to outperform all other competitive metrics on all tasks. We envision that SAMScore will prove to be a valuable tool that will help to drive the vibrant field of image translation, by allowing for more precise evaluations of new and evolving translation models. The code is available at https://github.com/Kent0n-Li/SAMScore.