mlsanityData to 14 Oct 2026

MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment

arXiv 2204.08958 ↗First posted 19 Apr 2022cs.CV eess.IVcited by 522

Not on the map. Why?

Cited by 164 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

No-Reference Image Quality Assessment (NR-IQA) aims to assess the perceptual quality of images in accordance with human subjective perception. Unfortunately, existing NR-IQA methods are far from meeting the needs of predicting accurate quality scores on GAN-based distortion images. To this end, we propose Multi-dimension Attention Network for no-reference Image Quality Assessment (MANIQA) to improve the performance on GAN-based distortion. We firstly extract features via ViT, then to strengthen global and local interactions, we propose the Transposed Attention Block (TAB) and the Scale Swin Transformer Block (SSTB). These two modules apply attention mechanisms across the channel and spatial dimension, respectively. In this multi-dimensional manner, the modules cooperatively increase the interaction among different regions of images globally and locally. Finally, a dual branch structure for patch-weighted quality prediction is applied to predict the final score depending on the weight of each patch's score. Experimental results demonstrate that MANIQA outperforms state-of-the-art methods on four standard datasets (LIVE, TID2013, CSIQ, and KADID-10K) by a large margin. Besides, our method ranked first place in the final testing phase of the NTIRE 2022 Perceptual Image Quality Assessment Challenge Track 2: No-Reference. Codes and models are available at https://github.com/IIGROUP/MANIQA.

Key facts. Cited by 522 papers in the map (data through 14 Oct 2026). Builds on 30 of its 61 references that are in the map. First posted on arXiv 19 Apr 2022.

Builds on

30 of 61 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  6. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  7. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  8. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  9. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  10. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  11. 2017The Perception-Distortion Tradeoffcited by 587
  12. 2020Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Cluescited by 523
18 more
  1. 2017NIMA: Neural Image Assessmentcited by 389
  2. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 302
  3. 2016Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessmentcited by 225
  4. 2019From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Qualitycited by 223
  5. 2020PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restorationcited by 178
  6. 2021No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistencycited by 166
  7. 2016Learning a No-Reference Quality Metric for Single-Image Super-Resolutioncited by 144
  8. 2020MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessmentcited by 144
  9. 2020Transformer for Image Quality Assessmentcited by 76
  10. 2019dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairscited by 73
  11. 2016Perceptual Quality Prediction on Authentically Distorted Images Using a Bag of Features Approachcited by 71
  12. 2018Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learningcited by 49
  13. 2021Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessmentcited by 41
  14. 2016On the Use of Deep Learning for Blind Image Quality Assessmentcited by 34
  15. 2020Assessing Image Quality Issues for Real-World Problemscited by 28
  16. 2021NTIRE 2021 Challenge on Perceptual Image Quality Assessmentcited by 18
  17. 2022VDTR: Video Deblurring with Transformercited by 15
  18. 2021Region-Adaptive Deformable Network for Image Quality Assessmentcited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 43; 2024: 104; 2025: 187; 2026: 184.

522 papers.

Sort:

By area:

  1. 2024OminiControl: Minimal and Universal Control for Diffusion Transformercited by 340
  2. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 315
  3. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 286
  4. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 280
  5. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 257
  6. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 246
  7. 2023TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessmentcited by 226
  8. 2025Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distributioncited by 141
  9. 2025Emu3.5: Native Multimodal Models are World Learnerscited by 132
  10. 2025EasyControl: Adding Efficient and Flexible Control for Diffusion Transformercited by 119
  11. 2025Q-Insight: Understanding Image Quality via Visual Reinforcement Learningcited by 98
  12. 2024Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approachcited by 97
38 more
  1. 2025Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understandingcited by 88
  2. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 87
  3. 2025VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rankcited by 79
  4. 2023CoSeR: Bridging Image and Language for Cognitive Super-Resolutioncited by 66
  5. 2024AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillationcited by 66
  6. 2024DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curationcited by 65
  7. 2025Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Modelscited by 65
  8. 2025UniVerse-1: Unified Audio-Video Generation via Stitching of Expertscited by 61
  9. 2025DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolutioncited by 53
  10. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 52
  11. 2024A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessmentcited by 43
  12. 2024An Intelligent Agentic System for Complex Image Restoration Problemscited by 43
  13. 2022NTIRE 2022 Challenge on Perceptual Image Quality Assessmentcited by 41
  14. 2023DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Modelscited by 41
  15. 2024XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolutioncited by 41
  16. 2025One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillationcited by 41
  17. 2024PromptFix: You Prompt and We Fix the Photocited by 40
  18. 2025OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpaintingcited by 39
  19. 2025VisualCloze: A Universal Image Generation Framework via Visual In-Context Learningcited by 39
  20. 2024Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Datasetcited by 38
  21. 2023DocDiff: Document Enhancement via Residual Diffusion Modelscited by 37
  22. 2024Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Drivingcited by 35
  23. 2025Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumptioncited by 35
  24. 2025JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restorationcited by 34
  25. 2024OSDFace: One-Step Diffusion Model for Face Restorationcited by 33
  26. 2024FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolutioncited by 32
  27. 2025FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generationcited by 32
  28. 2026LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generationcited by 30
  29. 2022Mitigating Artifacts in Real-World Video Super-Resolution Modelscited by 29
  30. 2025Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Modelcited by 29
  31. 2024Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecturecited by 28
  32. 2024Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolutioncited by 26
  33. 2023EVREAL: Towards a Comprehensive Benchmark and Analysis Suite for Event-based Video Reconstructioncited by 24
  34. 2023SPIRE: Semantic Prompt-Driven Image Restorationcited by 24
  35. 2024HoloDreamer: Holistic 3D Panoramic World Generation from Text Descriptionscited by 24
  36. 2025Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Modelscited by 24
  37. 2022AnimeSR: Learning Real-World Super-Resolution Models for Animation Videoscited by 23
  38. 2024NightHaze: Nighttime Image Dehazing via Self-Prior Learningcited by 23

50 most cited of 522 All 522 (JSON)