R2-B2: A Metric of Synthesized Image’s Photorealism by Regression Analysis based on Recognized Objects’ Bounding Box
Authors:
- 29 November 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
In recent years, a lot of researches on AI (Artificial Intelligence) for Image Synthesis and Image Generation have been being conducted actively, and state of the art GANs (Generative Adversarial Networks) for text-to-image have been able to generate precise images with high photorealism for a text-based user query (but also no-good images). However, it is pointed out that the precision of all images generated for a query has been not always enough high. Therefore, for practical usages, they are required to be re-ranked and/or filtered based on some sort of metric(s). This paper proposes a novel metric, R2-B2 (RR-BB), on photorealism, especially “size balance” (i.e., balance between in-image objects’ size), of a manually or automatically synthesized image by Regression analysis based on multiple Recognized objects’ Bounding Box, i.e., the position $(x, y)$ and size (width, height, or area) of objects recognized in the image.
Keywords
This publication has 17 references indexed in Scilit:
- 2D and 3D Image Quality Assessment: A Survey of Metrics and ChallengesIEEE Access, 2018
- A comparative analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK2018
- No-reference image quality assessment algorithms: A surveyOptik, 2015
- No-Reference Image Quality Assessment in the Spatial DomainIEEE Transactions on Image Processing, 2012
- Full-Reference Image Quality Metrics: Classification and EvaluationFoundations and Trends in Computer Graphics and Vision, 2012
- Reduced- and No-Reference Image Quality AssessmentIEEE Signal Processing Magazine, 2011
- Image Quality Metrics: PSNR vs. SSIM2010
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Full reference and reduced reference metrics for image quality assessment2003
- Image Quality Metrics2002