# Exploring Rich Subjective Quality Information for Image Quality Assessment in the Wild

arXiv: https://arxiv.org/abs/2409.05540 · HTML: https://mlsanity.com/paper/2409.05540/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 72 references that are in the map.
- First posted on arXiv 9 Sep 2024.

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Gated Graph Sequence Neural Networks](https://mlsanity.com/paper/1511.05493/) (2015)
- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment](https://mlsanity.com/paper/1910.06180/) (2019)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment](https://mlsanity.com/paper/2308.03060/) (2023)
- [Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment](https://mlsanity.com/paper/1612.01697/) (2016)
- [From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality](https://mlsanity.com/paper/1912.10088/) (2019)
- [Massive Online Crowdsourced Study of Subjective and Objective Picture Quality](https://mlsanity.com/paper/1511.02919/) (2015)
- [No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency](https://mlsanity.com/paper/2108.06858/) (2021)
- [Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Training](https://mlsanity.com/paper/2105.14550/) (2021)
- [GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessment](https://mlsanity.com/paper/2103.07666/) (2021)
- [Perceptual Video Quality Assessment: A Survey](https://mlsanity.com/paper/2402.03413/) (2024)
- [Continual Learning for Blind Image Quality Assessment](https://mlsanity.com/paper/2102.09717/) (2021)
- [Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop](https://mlsanity.com/paper/2210.00933/) (2022)
- [Task-Specific Normalization for Continual Learning of Blind Image Quality Models](https://mlsanity.com/paper/2107.13429/) (2021)
- [Perceptual Quality Assessment of Face Video Compression: A Benchmark and An Effective Method](https://mlsanity.com/paper/2304.07056/) (2023)
- [REQA: Coarse-to-fine Assessment of Image Quality to Alleviate the Range Effect](https://mlsanity.com/paper/2209.01760/) (2022)
- [User-generated Video Quality Assessment: A Subjective and Objective Study](https://mlsanity.com/paper/2005.08527/) (2020)

## Built on by (most cited first, 13 of 13)

- [T2VEval: Benchmark Dataset and Objective Evaluation Method for T2V-generated Videos](https://mlsanity.com/paper/2501.08545/) (2025)
- [Explore the Hallucination on Low-level Perception for MLLMs](https://mlsanity.com/paper/2409.09748/) (2024)
- [TechImage-Bench: Rubric-Based Evaluation for Technical Image Generation](https://mlsanity.com/paper/2512.12220/) (2025)
- [Mix-Modality Person Re-Identification: A New and Practical Paradigm](https://mlsanity.com/paper/2412.04719/) (2024)
- [Mitigating Low-Level Visual Hallucinations Requires Self-Awareness: Database, Model and Training Strategy](https://mlsanity.com/paper/2503.20673/) (2025)
- [OmniQuality-R: Advancing Reward Models Through All-Encompassing Quality Assessment](https://mlsanity.com/paper/2510.10609/) (2025)
- [CAST-LUT: Tokenizer-Guided HSV Look-Up Tables for Purple Flare Removal](https://mlsanity.com/paper/2511.06764/) (2025)
- [Surveillance Facial Image Quality Assessment: A Multi-dimensional Dataset and Lightweight Model](https://mlsanity.com/paper/2602.07403/) (2026)
- [Versatile Cataract Fundus Image Restoration Model Utilizing Unpaired Cataract and High-quality Images](https://mlsanity.com/paper/2411.12278/) (2024)
- [Swin Transformer for Robust CGI Images Detection: Intra- and Inter-Dataset Analysis across Multiple Color Spaces](https://mlsanity.com/paper/2505.16253/) (2025)
- [DocIQ: A Benchmark Dataset and Feature Fusion Network for Document Image Quality Assessment](https://mlsanity.com/paper/2509.17012/) (2025)
- [Contrastive Order Learning: A General Framework for Ordinal Regression](https://mlsanity.com/paper/2607.08109/) (2026)
- [Local SVD-Entropy Maps as a Complementary Structural Representation for Full-Reference and No-Reference Image Quality Assessment](https://mlsanity.com/paper/2609.27959/) (2026)

## Abstract (arXiv)

Traditional in the wild image quality assessment (IQA) models are generally trained with the quality labels of mean opinion score (MOS), while missing the rich subjective quality information contained in the quality ratings, for example, the standard deviation of opinion scores (SOS) or even distribution of opinion scores (DOS). In this paper, we propose a novel IQA method named RichIQA to explore the rich subjective rating information beyond MOS to predict image quality in the wild. RichIQA is characterized by two key novel designs: (1) a three-stage image quality prediction network which exploits the powerful feature representation capability of the Convolutional vision Transformer (CvT) and mimics the short-term and long-term memory mechanisms of human brain; (2) a multi-label training strategy in which rich subjective quality information like MOS, SOS and DOS are concurrently used to train the quality prediction network. Powered by these two novel designs, RichIQA is able to predict the image quality in terms of a distribution, from which the mean image quality can be subsequently obtained. Extensive experimental results verify that the three-stage network is tailored to predict rich quality information, while the multi-label training strategy can fully exploit the potentials within subjective quality rating and enhance the prediction performance and generalizability of the network. RichIQA outperforms state-of-the-art competitors on multiple large-scale in the wild IQA databases with rich subjective rating labels. The code of RichIQA will be made publicly available on GitHub.