Awesome Image Quality Assessment (IQA)

A comprehensive collection of IQA papers, datasets and codes. We also provide PyTorch implementations of mainstream metrics in IQA-PyTorch

• Awesome Image Quality Assessment (IQA)
  • Papers
    • Explainable IQA
    • AIGC IQA
    • No Reference (NR)
    • Full Reference (FR)
    • Image Aesthetic Assessment
    • Others
  • Datasets
    • IQA datasets
    • Perceptual similarity datasets

Related Resources:

• Awesome Image Aesthetic Assessment and Cropping. A curated list of resources including papers, datasets, and relevant links to aesthetic evaluation and cropping.

Papers

Unified IQA

All IQA types unified in a single model

• [ECCV 2024] PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts, Chen et al. Bibtex
• [ICML 2024] Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels, Wu et al. Github | Bibtex

Explainable IQA

Human readable IQA, mostly with large language models

• [TPAMI 2024] Q-Bench+: A Benchmark for Multi-modal Foundation Models on Low-level Vision from Single Images to Pairs, Zhang et al. Github | Bibtex
• [ACM MM2024] Q-Ground: Image Quality Grounding with Large Multi-modality Models, Chen et al. Bibtex | Github
• [Arxiv 2024] VisualCritic: Making LMMs Perceive Visual Quality Like Humans, Huang et al. Bibtex
• [ECCV 2024] A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment, Wu et al. Github | Bibtex
• [ECCV 2024] Towards Open-ended Visual Quality Comparison, Wu et al. Github | Bibtex
• [ECCV 2024] Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models, You et al. Project | Bibtex
• [CVPR 2024] Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models, Wu et al. Github | Bibtex

AIGC IQA

• ✨[CVPR 2024 (best paper)] Rich Human Feedback for Text-to-Image Generation, Liang et al. Github | Bibtex
• [ICLR 2024] Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision, Wu et al. Github | Bibtex
• [ICCV 2023] TIFA: Text-to-Image Faithfulness Evaluation with Question Answering, Hu et al. Github | Bibtex | Project
• [NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation, Xu et al. Github | Bibtex
• [ICCV2023] Better Aligning Text-to-Image Models with Human Preference, Wu et al. Github | Github(HPSv2) | Bibtex
• [NeurIPS 2023] Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation, Yuval et al. Github | Bibtex
• [TCSVT2023] A Fine-grained Subjective Perception & Alignment Database for AI Generated Image Quality Assessment, Li et al. Github | Bibtex

No Reference (NR)

• [Arxiv 2024] Q-Mamba: On First Exploration of Vision Mamba for Image Quality Assessment, Guan et al. Bibtex

• [Arxiv 2024] Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare, Zhe et al. Bibtex

• [Arxiv 2024] Quality-aware Image-Text Alignment for Real-World Image Quality Assessment, Agnolucci et al. Github | Bibtex

• [CVPR 2024] Bridging the Synthetic-to-Authentic Gap: Distortion-Guided Unsupervised Domain Adaptation for Blind Image Quality Assessment, Li et al. Bibtex

• [CVPR 2024] Boosting Image Quality Assessment through Efficient Transformer Adaptation with Local Feature Enhancement , Xu et al. | Bibtex

• [WACV2024] ARNIQA: Learning Distortion Manifold for Image Quality Assessment, Agnolucci et al. Github | Bibtex

• [TIP2023] TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment, Chen et al. Github | Bibtex

• [ICCV2023] Test Time Adaptation for Blind Image Quality Assessment, Roy et al. Github | Bibtex

• [CVPR2023] Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild, Saha et al. Bibtex | Github

• [CVPR2023] Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective, Zhang et al. Github | Bibtex

• [CVPR2023] Quality-aware Pre-trained Models for Blind Image Quality Assessment, Zhao et al. Bibtex

• [AAAI2023] Exploring CLIP for Assessing the Look and Feel of Images, Wang et al. Github | Bibtex

• [AAAI2023] Data-Efficient Image Quality Assessment with Attention-Panel Decoder, Qin et al. Github | Bibtex

• [TPAMI2022] Continual Learning for Blind Image Quality Assessment , Zhang et al. Github | Bibtex

• [TIP2022] No-Reference Image Quality Assessment by Hallucinating Pristine Features, Chen et al. Github | Bibtex

• [TIP2022] VCRNet: Visual Compensation Restoration Network for No-Reference Image Quality Assessment, Pan et al. Github | Bibtex

• [TMM2022] GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessment, Sun et al. Github | Bibtex

• [CVPR2021] Troubleshooting Blind Image Quality Models in the Wild, Wang et al. Github | Bibtex

Paper Link	Method	Type	Published	Code	Keywords
arXiv	MANIQA	NR	CVPRW2022	Official	Transformer, multi-dimension attention, dual branch
arXiv	TReS	NR	WACV2022	Official	Transformer, relative ranking, self-consistency
pdf	KonIQ++	NR	BMVC2021	Official	Multi-task with distortion prediction
arXiv	MUSIQ	NR	ICCV2021	Official / Pytorch	Multi-scale, transformer, Aspect Ratio Preserved (ARP) resizing
arXiv	CKDN	NR	ICCV2021	Official	Degraded reference, Conditional knowledge distillation (related to HIQA)
pdf	HyperIQA	NR	CVPR2020	Official	Content-aware hyper network
arXiv	Meta-IQA	NR	CVPR2020	Official	Meta-learning
arXiv	GIQA	NR	ECCV2020	Official	Generated image
arXiv	PI	NR	2018 PIRM Challenge	Project	1/2 * (NIQE + (10 - NRQM)).
arXiv	HIQA	NR	CVPR2018	Project	Hallucinated reference
arXiv	BPSQM	NR	CVPR2018		Pixel-wise quality map
arXiv	RankIQA	NR	ICCV2017	Github	Pretrain on synthetically ranked data
pdf	CNNIQA	NR	CVPR2014	PyTorch	First CNN-based NR-IQA
arXiv	UNIQUE	NR	TIP2021	Github	Combine synthetic and authentic image pairs
arXiv	DBCNN	NR	TCSVT2020	Official	Two branches for synthetic and authentic distortions
pdf	SFA	NR	TMM2019	Official	Aggregate ResNet50 features of multiple cropped patches
pdf/arXiv	PQR	NR/Aesthetic	TIP2019	Official1/Official2	Unify different type of aesthetic labels
arXiv	WaDIQaM (deepIQA)	NR/FR	TIP2018	PyTorch	Weighted average of patch qualities, shared FR/NR models
pdf	NIMA	NR	TIP2018	PyTorch/Tensorflow	Squared EMD loss
pdf	MEON	NR	TIP2017		Multi-task: distortion learning and quality prediction
arXiv	dipIQ	NR	TIP2017	download	Similar to RankIQA
arXiv	NRQM (Ma)	NR	CVIU2017	Project	Traditional, Super resolution
arXiv	FRIQUEE	NR	JoV2017	Official	Authentically Distorted, Bag of Features
IEEE	HOSA	NR	TIP2016	Matlab download	Traditional
pdf	ILNIQE	NR	TIP2015	Official	Traditional
pdf	BRISQUE	NR	TIP2012	Official	Traditional
pdf	BLIINDS-II	NR	TIP2012	Official
pdf	CORNIA	NR	CVPR2012	Matlab download	Codebook Representation
pdf	NIQE	NR	SPL2012	Official	Traditional
pdf	DIIVINE	NR	TIP2011	Official

Full Reference (FR)

• [ECCV2022] Shift-tolerant Perceptual Similarity Metric, Ghildyal et al. Github | Bibtex
• [BMVC2022] Content-Diverse Comparisons improve IQA, Thong et al. Bibtex
• [ACM MM2022] Quality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical Fidelity, Zhou et al. Github | Bibtex

Paper Link	Method	Type	Published	Code	Keywords
arXiv	AHIQ	FR	CVPR2022 NTIRE workshop	Official	Attention, Transformer
arXiv	JSPL	FR	CVPR2022	Official	semi-supervised and positive-unlabeled (PU) learning
arXiv	CVRKD	NAR	AAAI2022	Official	Non-Aligned content reference, knowledge distillation
arXiv	IQT	FR	CVPRW2021	PyTorch	Transformer
arXiv	A-DISTS	FR	ACMM2021	Official
arXiv	DISTS	FR	TPAMI2021	Official
arXiv	LPIPS	FR	CVPR2018	Project	Perceptual similarity, Pairwise Preference
arXiv	PieAPP	FR	CVPR2018	Project	Perceptual similarity, Pairwise Preference
arXiv	WaDIQaM	NR/FR	TIP2018	Official
arXiv	JND-SalCAR	FR	TCSVT2020		JND (Just-Noticeable-Difference)
pdf	QADS	FR	TIP2019	Project	Super-resolution
pdf	FSIM	FR	TIP2011	Project	Traditional
pdf	VIF/IFC	FR	TIP2006	Project	Traditional
pdf	MS-SSIM	FR		Project	Traditional
pdf	SSIM	FR	TIP2004	Project	Traditional
	PSNR	FR			Traditional

Image Aesthetic Assessment

• [ACMMM 2024] AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception, Huang et al. Project | Github | Bibtex
• [Arxiv 2024] AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception, Huang et al. Github | Bibtex
• [ECCV2024] Scaling Up Personalized Aesthetic Assessment via Task Vector Arithmetic, Yun et al. Bibtex | Project
• [CVPR2023] VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining, Ke et al. Bibtex
• [CVPR2023] Towards Artistic Image Aesthetics Assessment: a Large-scale Dataset and a New Method, Yi et al. Github | Bibtex

Others

Color IQA

• [ECCV 2024] Multiscale Sliced Wasserstein Distances as Perceptual Color Difference Measures, He et al. Github | Bibtex
• [CVPR 2023] Learning a Deep Color Difference Metric for Photographic Images, Chen et al. Github | Bibtex

Face IQA

• [CVPR2024] DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformer, Chen et al. Bibtex | Project

360° Image (Omnidirectional Image) IQA

• [NeurIPS 2023] Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment , Wu et al. Bibtex | Github

Egocentric Spatial Images (Apple Vision Pro)

• [Arxiv 2024] ESIQA: Perceptual Quality Assessment of Vision-Pro-based Egocentric Spatial Images, Zhu et al. Bibtex | Github

Adversarial Attack on IQA

• [Arxiv 2024] Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics, Gushchin et al. Bibtex | Github | Project
• [NeurIPS 2022] Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop, Zhang et al. Bibtex | Github

IQA Losses

Title	Method	Published	Code	Keywords
arXiv	NiNLoss	ACMM2020	Official	Norm-in-Norm Loss

Datasets

IQA datasets

Paper Link	Dataset Name	Type	Published	Website	Images	Annotations
arXiv	UHD-IQA	NR	ECCVW2024	Project	6k (~3840x2160)	20 ratings per image
arXiv	PaQ-2-PiQ	NR	CVPR2020	Official github	40k, 120k patches	4M
CVF	SPAQ	NR	CVPR2020	Offical github	11k (smartphone)
arXiv	KonIQ-10k	NR	TIP2020	Project	10k from YFCC100M	1.2M
arXiv	AADB	NR/Aesthentic	ECCV2016	Official github	10k images (8500/500/1000), 11 attributes
arXiv	CLIVE	NR	TIP2016	Project	1200	350k
pdf	AVA	NR / Aesthentic	CVPR2012	Github/Project	250k (60 categories)
arXiv	PIPAL	FR	ECCV2020	Project	250	1.13M
arXiv	KADIS-700k	FR	arXiv	Project	140k pristine / 700k distorted	30 ratings (DCRs) per image.
IEEE	KADID-10k	FR	QoMEX2019	Project	81	10k distortions
pdf	Waterloo-Exp	FR	TIP2017	Project	4744	94k distortions
pdf	MDID	FR	PR2017	---	20	1600 distortions
pdf	TID2013	FR	SP2015	Project	25	3000 distortions
pdf	LIVEMD	FR	ACSSC2012	Project	15 pristine images	two successive distortions
pdf	CSIQ	FR	Journal of Electronic Imaging 2010	---	30	866 distortions
pdf	TID2008	FR	2009	Project	25	1700 distortions
pdf	LIVE IQA	FR	TIP2006	Project	29 images, 780 synthetic distortions
link	IVC	FR	2005	---	10	185 distortions

Perceptual similarity datasets

Paper Title	Dataset Name	Type	Published	Website	Images	Annotations
arXiv	BAPPS(LPIPS)	FR	CVPR2018	Project	187.7k	484k
arXiv	PieAPP	FR	CVPR2018	Project	200 images	2.3M