Image generation evaluation: a comprehensive survey of human and automatic evaluations
- 1 July 2025
- journal article
- Published by Zhejiang University Press in Frontiers of Information Technology & Electronic Engineering
- Vol. 26 (7) , 1027-1065
Abstract
Image generation models have made remarkable progress, and image evaluation is crucial for explaining and driving the development of these models. PreviousKeywords
This publication has 171 references indexed in Scilit:
- Evaluating Text-to-Visual Generation with Image-to-Text Generation2024
- Manipulated Face Detection and Localization Based on Semantic Segmentation2023
- Amodal Layout Completion in Complex Outdoor Scenes2022
- TISE: Bag of Metrics for Text-to-Image Synthesis Evaluation2022
- Trace Controlled Text to Image Generation2022
- BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-Aided Adversarial Learning2022
- XingGAN for Person Image Generation2020
- Transforming and Projecting Images into Class-Conditional Generative Networks2020
- Generative Semantic Manipulation with Mask-Contrasting GAN2018
- High‐Quality Panoramic Image Generation Using Multiple PAL ImagesElectronics and Communications in Japan, 2014