Research records on Image Semantic Similarity/Image Semantic Quality/Image Semantic Assessment
| Paper | First Author | Time |
|---|---|---|
| A Survey on Quality Metrics for Text-to-Image Generation | Sebastian Hartwig | 2024.03 |
| Towards Better Text-Image Consistency in Text-to-Image Generation | Zhaorui Tan | 2022.10 |
| Semantic Feature Decomposition based Semantic Communication System of Images with Large-scale Visual Generation Models | Senran Fa | 2024.10 |
| Semantic Similarity Score for Measuring Visual Similarity at Semantic Level | Senran Fan | 2024.06 |
| Toward Semantic Communications: Deep Learning-Based Image Semantic Coding | Danlan Huang | 2023.01 |
| TOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment | Chaofeng Chen | 2024.04 |
| GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium(FID) | Martin Heusel | 2017.04 |
| Improved Precision and Recall Metric for Assessing Generative Models(KPR) | Tuomas Kynkäänniemi | 2019.10 |
| Improved Techniques for Training GANs(IS) | Tim Salimans | 2016.10 |
Paper sources for commonly used datasets
| Paper | Years | Used dataset | Dataset corresponding to reference |
|---|---|---|---|
| A Survey on Quality Metrics for Text-to-Image Generation | 2025 | A large number of unpublished datasets, but most of the datasets come from Flicker.com, VOC2008, COCO, Open images, Pinerest.com | Pinerest：Training and evaluating multimodal word embeddings with large-scale web annotated images VOC2008：Pascal VOC 2008 challenge Openimages：The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale |
| SSD:Towards Better Text-Image Consistency in Text-to-Image Generation | 2022 | COCO, CUB | COCO：Microsoft coco: Common objects in context CUB：The caltech-ucsd birds-200-2011 dataset |
| TOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment | 2024 | LIVE, CSIQ, KADID-10K, PieAPP, BAPPS, PIPAL, CLIVE, KonIQ-10k, SPAQ, AVA, FLIVE | LIVE：A statistical evaluation of recent full reference image quality assessment algorithms CSIQ：Most apparent distortion: Full-reference image quality assessment and the role of strategy TID-2013：Color image database TID2013: Peculiarities and preliminary results KADID-10K：A large-scale artificially distorted IQA database PieAPP：Perceptual imageerror assessment through pairwise preference BAPPS：The unreasonable effectiveness of deep features as a perceptual metric PIPAL：A largescale image quality assessment dataset for perceptual image restoration CLIVE：A largescale image quality assessment dataset for perceptual image restoration KonIQ-10k： KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment SPAQ：Perceptual quality assessment of smartphone photography AVA：AVA: A large-scale database for aesthetic visual analysis FLIVE：From patches to pictures (PaQ-2-PiQ): Mapping the perceptual space of picture quality |
| Semantic Feature Decomposition based Semantic Communication System of Images with Large-scale Visual Generation Models | 2024 | COCO | COCO：Microsoft coco: Common objects in context |
| Toward Semantic Communications: Deep Learning-Based Image Semantic Coding | 2023 | Cityscapes | Cityscapes：The cityscapes dataset for semantic urban scene understanding |
| Joint Autoregressive and Hierarchical Priors for Learned Image Compression | 2018 | Kodak | Most of the results of coding papers come from Kodak: Kodak Lossless True Color Image Suite (PhotoCD PCD0992) |
| ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding | 2022 | ImageNet | ImageNet：Imagenet: A large-scale hierarchical image database. |