# ARNIQA: Learning Distortion Manifold for Image Quality Assessment

arXiv: https://arxiv.org/abs/2310.14918 · HTML: https://mlsanity.com/paper/2310.14918/

## 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 (most cited first, 26 of 26)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality](https://mlsanity.com/paper/1912.10088/) (2019)
- [No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency](https://mlsanity.com/paper/2108.06858/) (2021)
- [PieAPP: Perceptual Image-Error Assessment through Pairwise Preference](https://mlsanity.com/paper/1806.02067/) (2018)
- [Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild](https://mlsanity.com/paper/2304.00451/) (2023)
- [A Probabilistic Quality Representation Approach to Deep Blind Image Quality Prediction](https://mlsanity.com/paper/1708.08190/) (2017)
- [Assessing Image Quality Issues for Real-World Problems](https://mlsanity.com/paper/2003.12511/) (2020)
- [Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel](https://mlsanity.com/paper/2107.00986/) (2021)
- [A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds](https://mlsanity.com/paper/2205.04910/) (2022)
- [Quality-aware Pre-trained Models for Blind Image Quality Assessment](https://mlsanity.com/paper/2303.00521/) (2023)

## Built on by (most cited first, 30 of 89)

- [SkyReels-V2: Infinite-length Film Generative Model](https://mlsanity.com/paper/2504.13074/) (2025)
- [Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessment](https://mlsanity.com/paper/2403.11176/) (2024)
- [NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild](https://mlsanity.com/paper/2604.11487/) (2026)
- [MIRA: Multimodal Iterative Reasoning Agent for Image Editing](https://mlsanity.com/paper/2511.21087/) (2025)
- [UHD-IQA Benchmark Database: Pushing the Boundaries of Blind Photo Quality Assessment](https://mlsanity.com/paper/2406.17472/) (2024)
- [Video Quality Assessment: A Comprehensive Survey](https://mlsanity.com/paper/2412.04508/) (2024)
- [DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild](https://mlsanity.com/paper/2405.19996/) (2024)
- [Image Quality Assessment: From Human to Machine Preference](https://mlsanity.com/paper/2503.10078/) (2025)
- [Assessing UHD Image Quality from Aesthetics, Distortions, and Saliency](https://mlsanity.com/paper/2409.00749/) (2024)
- [HarmonyIQA: Pioneering Benchmark and Model for Image Harmonization Quality Assessment](https://mlsanity.com/paper/2501.01116/) (2025)
- [Exploiting Deblurring Networks for Radiance Fields](https://mlsanity.com/paper/2502.14454/) (2025)
- [Augmenting Perceptual Super-Resolution via Image Quality Predictors](https://mlsanity.com/paper/2504.18524/) (2025)
- [Hallucination Score: Towards Mitigating Hallucinations in Generative Image Super-Resolution](https://mlsanity.com/paper/2507.14367/) (2025)
- [LAR-IQA: A Lightweight, Accurate, and Robust No-Reference Image Quality Assessment Model](https://mlsanity.com/paper/2408.17057/) (2024)
- [AIM 2024 Challenge on UHD Blind Photo Quality Assessment](https://mlsanity.com/paper/2409.16271/) (2024)
- [GenDR: Lighten Generative Detail Restoration](https://mlsanity.com/paper/2503.06790/) (2025)
- [Parametric Shadow Control for Portrait Generation in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2503.21943/) (2025)
- [Losing the Plot: How VLM responses degrade on imperfect charts](https://mlsanity.com/paper/2509.18425/) (2025)
- [QualiTeacher: Quality-Conditioned Pseudo-Labeling for Real-World Image Restoration](https://mlsanity.com/paper/2603.08030/) (2026)
- [Deep Joint Unrolling for Deblurring and Low-Light Image Enhancement (JUDE)](https://mlsanity.com/paper/2412.07527/) (2024)
- [TRIQA: Image Quality Assessment by Contrastive Pretraining on Ordered Distortion Triplets](https://mlsanity.com/paper/2507.12687/) (2025)
- [After the Party: Navigating the Mapping From Color to Ambient Lighting](https://mlsanity.com/paper/2508.02168/) (2025)
- [Image and Video Quality Assessment using Prompt-Guided Latent Diffusion Models for Cross-Dataset Generalization](https://mlsanity.com/paper/2406.04654/) (2024)
- [Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunities](https://mlsanity.com/paper/2410.08534/) (2024)
- [IQPFR: An Image Quality Prior for Blind Face Restoration and Beyond](https://mlsanity.com/paper/2503.09294/) (2025)
- [Efficient Face Image Quality Assessment via Self-training and Knowledge Distillation](https://mlsanity.com/paper/2507.15709/) (2025)
- [Rethinking Inter-LoRA Orthogonality in Adapter Merging: Insights from Orthogonal Monte Carlo Dropout](https://mlsanity.com/paper/2510.03262/) (2025)
- [Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration](https://mlsanity.com/paper/2603.29773/) (2026)
- [Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution](https://mlsanity.com/paper/2502.06476/) (2025)
- [DGIQA: Depth-guided Feature Attention and Refinement for Generalizable Image Quality Assessment](https://mlsanity.com/paper/2505.24002/) (2025)

## 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.