mlsanityData to 14 Oct 2026

ARNIQA: Learning Distortion Manifold for Image Quality Assessment

arXiv 2310.14918 ↗First posted 20 Oct 2023cs.CVcited by 89

Not on the map. Why?

Abstract (arXiv)

No-Reference Image Quality Assessment (NR-IQA) aims to develop methods to measure image quality in alignment with human perception without the need for a high-quality reference image. In this work, we propose a self-supervised approach named ARNIQA (leArning distoRtion maNifold for Image Quality Assessment) for modeling the image distortion manifold to obtain quality representations in an intrinsic manner. First, we introduce an image degradation model that randomly composes ordered sequences of consecutively applied distortions. In this way, we can synthetically degrade images with a large variety of degradation patterns. Second, we propose to train our model by maximizing the similarity between the representations of patches of different images distorted equally, despite varying content. Therefore, images degraded in the same manner correspond to neighboring positions within the distortion manifold. Finally, we map the image representations to the quality scores with a simple linear regressor, thus without fine-tuning the encoder weights. The experiments show that our approach achieves state-of-the-art performance on several datasets. In addition, ARNIQA demonstrates improved data efficiency, generalization capabilities, and robustness compared to competing methods. The code and the model are publicly available at https://github.com/miccunifi/ARNIQA.

Key facts. Cited by 89 papers in the map (data through 14 Oct 2026). Builds on 26 of its 58 references that are in the map. First posted on arXiv 20 Oct 2023.

Builds on

26 of 58 references.

References · 26

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  7. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  8. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  9. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  10. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  11. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  12. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
14 more
  1. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 811
  2. 2020Contrastive Learning with Hard Negative Samplescited by 628
  3. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 529
  4. 2020Hard Negative Mixing for Contrastive Learningcited by 402
  5. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 302
  6. 2019From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Qualitycited by 223
  7. 2021No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistencycited by 166
  8. 2018PieAPP: Perceptual Image-Error Assessment through Pairwise Preferencecited by 160
  9. 2023Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wildcited by 97
  10. 2017A Probabilistic Quality Representation Approach to Deep Blind Image Quality Predictioncited by 28
  11. 2020Assessing Image Quality Issues for Real-World Problemscited by 28
  12. 2021Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernelcited by 27
  13. 2022A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Boundscited by 22
  14. 2023Quality-aware Pre-trained Models for Blind Image Quality Assessmentcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 16; 2025: 43; 2026: 30.

89 papers.

Sort:

By area:

  1. 2025SkyReels-V2: Infinite-length Film Generative Modelcited by 229
  2. 2024Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessmentcited by 32
  3. 2026NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wildcited by 18
  4. 2025MIRA: Multimodal Iterative Reasoning Agent for Image Editingcited by 17
  5. 2024UHD-IQA Benchmark Database: Pushing the Boundaries of Blind Photo Quality Assessmentcited by 16
  6. 2024Video Quality Assessment: A Comprehensive Surveycited by 15
  7. 2024DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wildcited by 14
  8. 2025Image Quality Assessment: From Human to Machine Preferencecited by 12
  9. 2024Assessing UHD Image Quality from Aesthetics, Distortions, and Saliencycited by 9
  10. 2025HarmonyIQA: Pioneering Benchmark and Model for Image Harmonization Quality Assessmentcited by 7
  11. 2025Exploiting Deblurring Networks for Radiance Fieldscited by 7
  12. 2025Augmenting Perceptual Super-Resolution via Image Quality Predictorscited by 7
38 more
  1. 2025Hallucination Score: Towards Mitigating Hallucinations in Generative Image Super-Resolutioncited by 6
  2. 2024LAR-IQA: A Lightweight, Accurate, and Robust No-Reference Image Quality Assessment Modelcited by 5
  3. 2024AIM 2024 Challenge on UHD Blind Photo Quality Assessmentcited by 5
  4. 2025GenDR: Lighten Generative Detail Restorationcited by 5
  5. 2025Parametric Shadow Control for Portrait Generation in Text-to-Image Diffusion Modelscited by 5
  6. 2025Losing the Plot: How VLM responses degrade on imperfect chartscited by 5
  7. 2026QualiTeacher: Quality-Conditioned Pseudo-Labeling for Real-World Image Restorationcited by 5
  8. 2024Deep Joint Unrolling for Deblurring and Low-Light Image Enhancement (JUDE)cited by 4
  9. 2025TRIQA: Image Quality Assessment by Contrastive Pretraining on Ordered Distortion Tripletscited by 4
  10. 2025After the Party: Navigating the Mapping From Color to Ambient Lightingcited by 4
  11. 2024Image and Video Quality Assessment using Prompt-Guided Latent Diffusion Models for Cross-Dataset Generalizationcited by 3
  12. 2024Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunitiescited by 3
  13. 2025IQPFR: An Image Quality Prior for Blind Face Restoration and Beyondcited by 3
  14. 2025Efficient Face Image Quality Assessment via Self-training and Knowledge Distillationcited by 3
  15. 2025Rethinking Inter-LoRA Orthogonality in Adapter Merging: Insights from Orthogonal Monte Carlo Dropoutcited by 3
  16. 2026Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restorationcited by 3
  17. 2025Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolutioncited by 2
  18. 2025DGIQA: Depth-guided Feature Attention and Refinement for Generalizable Image Quality Assessmentcited by 2
  19. 2025Latent Guidance in Diffusion Models for Perceptual Evaluationscited by 2
  20. 2025BPCLIP: A Bottom-up Image Quality Assessment from Distortion to Semantics Based on CLIPcited by 2
  21. 2025Concept-based Adversarial Attack: a Probabilistic Perspectivecited by 2
  22. 2025AgenticIQA: An Agentic Framework for Adaptive and Interpretable Image Quality Assessmentcited by 2
  23. 2025AIM 2025 Challenge on Real-World RAW Image Denoisingcited by 2
  24. 2025TechImage-Bench: Rubric-Based Evaluation for Technical Image Generationcited by 2
  25. 2025Guiding Perception-Reasoning Closer to Human in Blind Image Quality Assessmentcited by 2
  26. 2026POCI-Diff: 3D-Layout Guided Diffusion for Controllable Synthetic Surveillance Data Generationcited by 2
  27. 2026An Extensible and Lightweight Unified Architecture for Demosaicing Pixel-bin Image Sensorscited by 2
  28. 2024MSLIQA: Enhancing Learning Representations for Image Quality Assessment through Multi-Scale Learningcited by 1
  29. 2024MobileIQA: Exploiting Mobile-level Diverse Opinion Network For No-Reference Image Quality Assessment Using Knowledge Distillationcited by 1
  30. 2024Subjective and Objective Quality Evaluation of Super-Resolution Enhanced Broadcast Images on a Novel SR-IQA Datasetcited by 1
  31. 2025MMP-2K: A Benchmark Multi-Labeled Macro Photography Image Quality Assessment Databasecited by 1
  32. 2025HiRQA: Hierarchical Ranking and Quality Alignment for Opinion-Unaware Image Quality Assessmentcited by 1
  33. 2025OmniQuality-R: Advancing Reward Models Through All-Encompassing Quality Assessmentcited by 1
  34. 2025Non-Aligned Reference Image Quality Assessment for Novel View Synthesiscited by 1
  35. 2025VITAL: Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessmentcited by 1
  36. 2025Building Reasonable Inference for Vision-Language Models in Blind Image Quality Assessmentcited by 1
  37. 2026Decoupling Perception and Calibration: Label-Efficient Image Quality Assessment Frameworkcited by 1
  38. 2026ELIQ: A Label-Free Framework for Quality Assessment of Evolving AI-Generated Imagescited by 1

50 most cited of 89 All 89 (JSON)