SAMScore: A Content Structural Similarity Metric for Image Translation Evaluation
- 29 January 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 6 (8) , 2027-2040
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.Keywords
All Related Versions
Funding Information
- National Institutes of Health (R01 EB034691, R01 CA240808, R01 CA258987, R01 CA280135)
This publication has 33 references indexed in Scilit:
- SynthRAD2023 Grand Challenge dataset: Generating synthetic CT for radiotherapyMedical Physics, 2023
- Segmentation, Classification, and Registration of Multi-modality Medical Imaging Data2021
- Contrastive Learning for Unpaired Image-to-Image Translation2020
- MedGAN: Medical image translation using GANsComputerized Medical Imaging and Graphics, 2020
- Overview of image-to-image translation by use of deep neural networks: denoising, super-resolution, modality conversion, and reconstruction in medical imagingRadiological Physics and Technology, 2019
- Pros and cons of GAN evaluation measuresComputer Vision and Image Understanding, 2019
- Multimodal Unsupervised Image-to-Image Translation2018
- Spatial Pattern Templates for Recognition of Objects with Regular Structure2013
- Running experiments on Amazon Mechanical TurkJudgment and Decision Making, 2010
- Piecewise Affine Registration of Biological ImagesLecture Notes in Computer Science, 2003