# Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption

arXiv: https://arxiv.org/abs/2503.11221 · HTML: https://mlsanity.com/paper/2503.11221/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 62 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [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)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution](https://mlsanity.com/paper/2311.16518/) (2023)
- [Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild](https://mlsanity.com/paper/2401.13627/) (2024)
- [Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective](https://mlsanity.com/paper/2303.14968/) (2023)
- [Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization](https://mlsanity.com/paper/2308.14469/) (2023)
- [One-Step Effective Diffusion Network for Real-World Image Super-Resolution](https://mlsanity.com/paper/2406.08177/) (2024)
- [SinSR: Diffusion-Based Image Super-Resolution in a Single Step](https://mlsanity.com/paper/2311.14760/) (2023)
- [TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment](https://mlsanity.com/paper/2308.03060/) (2023)
- [PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration](https://mlsanity.com/paper/2007.12142/) (2020)
- [RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution](https://mlsanity.com/paper/1908.06382/) (2019)
- [Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution](https://mlsanity.com/paper/2501.11561/) (2025)
- [Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild](https://mlsanity.com/paper/2005.13983/) (2020)
- [Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution](https://mlsanity.com/paper/2203.09195/) (2022)
- [Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach](https://mlsanity.com/paper/2412.03017/) (2024)

## Built on by (most cited first, 30 of 35)

- [Q-Insight: Understanding Image Quality via Visual Reinforcement Learning](https://mlsanity.com/paper/2503.22679/) (2025)
- [VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank](https://mlsanity.com/paper/2505.14460/) (2025)
- [Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training](https://mlsanity.com/paper/2507.20291/) (2025)
- [Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling](https://mlsanity.com/paper/2602.11146/) (2026)
- [UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement](https://mlsanity.com/paper/2512.06750/) (2025)
- [VOSR: A Vision-Only Generative Model for Image Super-Resolution](https://mlsanity.com/paper/2604.03225/) (2026)
- [Bridging the Perception Gap in Image Super-Resolution Evaluation](https://mlsanity.com/paper/2503.13074/) (2025)
- [MarkSweep: A No-box Removal Attack on AI-Generated Image Watermarking via Noise Intensification and Frequency-aware Denoising](https://mlsanity.com/paper/2602.15364/) (2026)
- [GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-Resolution](https://mlsanity.com/paper/2603.16769/) (2026)
- [DeQA-Doc: Adapting DeQA-Score to Document Image Quality Assessment](https://mlsanity.com/paper/2507.12796/) (2025)
- [DP2O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution](https://mlsanity.com/paper/2510.18851/) (2025)
- [Beyond the Ground Truth: Enhanced Supervision for Image Restoration](https://mlsanity.com/paper/2512.03932/) (2025)
- [How far have we gone in Generative Image Restoration? A study on its capability, limitations and evaluation practices](https://mlsanity.com/paper/2603.05010/) (2026)
- [PixRestore: Unified Image Restoration via Pixel Diffusion Transformer](https://mlsanity.com/paper/2608.16793/) (2026)
- [Self-Supervised Image Super-Resolution Quality Assessment based on Content-Free Multi-Model Oriented Representation Learning](https://mlsanity.com/paper/2602.10744/) (2026)
- [Position: Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered](https://mlsanity.com/paper/2603.00643/) (2026)
- [OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution](https://mlsanity.com/paper/2603.12811/) (2026)
- [Banana100: Breaking NR-IQA Metrics by 100 Iterative Image Replications with Nano Banana Pro](https://mlsanity.com/paper/2604.03400/) (2026)
- [GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration](https://mlsanity.com/paper/2605.31039/) (2026)
- [Tool-IQA: Augmenting Image Quality Assessment with Simple Tools](https://mlsanity.com/paper/2606.16082/) (2026)
- [The Unanticipated Asymmetry Between Perceptual Optimization and Assessment](https://mlsanity.com/paper/2509.20878/) (2025)
- [PreResQ-R1: Response-Preference Disentangled Ranking-and-Scoring Reinforcement Optimization for Robust Visual Quality Assessment](https://mlsanity.com/paper/2511.05393/) (2025)
- [SDGIC: A Semantic Disambiguation-Guided Generative Image Compression Method for Ultra-Low Bitrates](https://mlsanity.com/paper/2512.06344/) (2025)
- [Evaluating and Preserving High-level Fidelity in Super-Resolution](https://mlsanity.com/paper/2512.07037/) (2025)
- [VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thought](https://mlsanity.com/paper/2603.22998/) (2026)
- [RefReward-SR: LR-Conditioned Reward Modeling for Preference-Aligned Super-Resolution](https://mlsanity.com/paper/2603.24198/) (2026)
- [Viewport-Unaware Blind Omnidirectional Image Quality Assessment: A Unified and Generalized Approach](https://mlsanity.com/paper/2604.23953/) (2026)
- [Hist2Style: Histogram-Guided Stylization with Bilateral Grids](https://mlsanity.com/paper/2606.01819/) (2026)
- [When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM Editing](https://mlsanity.com/paper/2606.07171/) (2026)
- [Adaptive Densification for High-Fidelity and Efficient Sparse Gaussian Splatting in Arbitrary-Scale Super-Resolution](https://mlsanity.com/paper/2606.29400/) (2026)

## Abstract (arXiv)

Full-reference image quality assessment (FR-IQA) generally assumes that reference images are of perfect quality. However, this assumption is flawed due to the sensor and optical limitations of modern imaging systems. Moreover, recent generative enhancement methods are capable of producing images of higher quality than their original. All of these challenge the effectiveness and applicability of current FR-IQA models. To relax the assumption of perfect reference image quality, we build a large-scale IQA database, namely DiffIQA, containing approximately 180,000 images generated by a diffusion-based image enhancer with adjustable hyper-parameters. Each image is annotated by human subjects as either worse, similar, or better quality compared to its reference. Building on this, we present a generalized FR-IQA model, namely Adaptive Fidelity-Naturalness Evaluator (A-FINE), to accurately assess and adaptively combine the fidelity and naturalness of a test image. A-FINE aligns well with standard FR-IQA when the reference image is much more natural than the test image. We demonstrate by extensive experiments that A-FINE surpasses standard FR-IQA models on well-established IQA datasets and our newly created DiffIQA. To further validate A-FINE, we additionally construct a super-resolution IQA benchmark (SRIQA-Bench), encompassing test images derived from ten state-of-the-art SR methods with reliable human quality annotations. Tests on SRIQA-Bench re-affirm the advantages of A-FINE. The code and dataset are available at https://tianhewu.github.io/A-FINE-page.github.io/.