# TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment

arXiv: https://arxiv.org/abs/2308.03060 · HTML: https://mlsanity.com/paper/2308.03060/

## Key facts

- Cited by 226 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 89 references that are in the map.
- First posted on arXiv 6 Aug 2023.

## Builds on (most cited first, 30 of 40)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [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)
- [Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective](https://mlsanity.com/paper/2303.14968/) (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)
- [Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index](https://mlsanity.com/paper/1308.3052/) (2013)
- [PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration](https://mlsanity.com/paper/2007.12142/) (2020)
- [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)
- [The 2018 PIRM Challenge on Perceptual Image Super-resolution](https://mlsanity.com/paper/1809.07517/) (2018)
- [RankIQA: Learning from Rankings for No-reference Image Quality Assessment](https://mlsanity.com/paper/1707.08347/) (2017)
- [Learning a No-Reference Quality Metric for Single-Image Super-Resolution](https://mlsanity.com/paper/1612.05890/) (2016)
- [MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2004.05508/) (2020)
- [AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2306.04717/) (2023)
- [Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation](https://mlsanity.com/paper/2003.10275/) (2020)
- [Transformer for Image Quality Assessment](https://mlsanity.com/paper/2101.01097/) (2020)
- [Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Training](https://mlsanity.com/paper/2105.14550/) (2021)
- [Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network](https://mlsanity.com/paper/2204.10485/) (2022)

## Built on by (most cited first, 30 of 226)

- [Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models](https://mlsanity.com/paper/2311.06783/) (2023)
- [HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer](https://mlsanity.com/paper/2505.22705/) (2025)
- [Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare](https://mlsanity.com/paper/2405.19298/) (2024)
- [A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment](https://mlsanity.com/paper/2403.10854/) (2024)
- [One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation](https://mlsanity.com/paper/2502.01993/) (2025)
- [Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption](https://mlsanity.com/paper/2503.11221/) (2025)
- [GoodDrag: Towards Good Practices for Drag Editing with Diffusion Models](https://mlsanity.com/paper/2404.07206/) (2024)
- [AIGIQA-20K: A Large Database for AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2404.03407/) (2024)
- [HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer](https://mlsanity.com/paper/2605.11061/) (2026)
- [Enhancing Diffusion Models with Text-Encoder Reinforcement Learning](https://mlsanity.com/paper/2311.15657/) (2023)
- [R-Bench: Are your Large Multimodal Model Robust to Real-world Corruptions?](https://mlsanity.com/paper/2410.05474/) (2024)
- [Compressed Image Generation with Denoising Diffusion Codebook Models](https://mlsanity.com/paper/2502.01189/) (2025)
- [Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models](https://mlsanity.com/paper/2503.11073/) (2025)
- [Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training](https://mlsanity.com/paper/2507.20291/) (2025)
- [SSUMamba: Spatial-Spectral Selective State Space Model for Hyperspectral Image Denoising](https://mlsanity.com/paper/2405.01726/) (2024)
- [Face Anonymization Made Simple](https://mlsanity.com/paper/2411.00762/) (2024)
- [Omni-ID: Holistic Identity Representation Designed for Generative Tasks](https://mlsanity.com/paper/2412.09694/) (2024)
- [Iterative Predictor-Critic Code Decoding for Real-World Image Dehazing](https://mlsanity.com/paper/2503.13147/) (2025)
- [MIRA: Multimodal Iterative Reasoning Agent for Image Editing](https://mlsanity.com/paper/2511.21087/) (2025)
- [Video Quality Assessment: A Comprehensive Survey](https://mlsanity.com/paper/2412.04508/) (2024)
- [TurboFill: Adapting Few-step Text-to-image Model for Fast Image Inpainting](https://mlsanity.com/paper/2504.00996/) (2025)
- [PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts](https://mlsanity.com/paper/2403.04993/) (2024)
- [Benchmarking Multi-dimensional AIGC Video Quality Assessment: A Dataset and Unified Model](https://mlsanity.com/paper/2407.21408/) (2024)
- [Exploring Rich Subjective Quality Information for Image Quality Assessment in the Wild](https://mlsanity.com/paper/2409.05540/) (2024)
- [Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs](https://mlsanity.com/paper/2409.17778/) (2024)
- [SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning](https://mlsanity.com/paper/2411.10161/) (2024)
- [Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessment](https://mlsanity.com/paper/2411.17237/) (2024)
- [Image Quality Assessment: From Human to Machine Preference](https://mlsanity.com/paper/2503.10078/) (2025)
- [MoA-VR: A Mixture-of-Agents System Towards All-in-One Video Restoration](https://mlsanity.com/paper/2510.08508/) (2025)
- [KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception](https://mlsanity.com/paper/2503.10259/) (2025)

## Abstract (arXiv)

Image Quality Assessment (IQA) is a fundamental task in computer vision that has witnessed remarkable progress with deep neural networks. Inspired by the characteristics of the human visual system, existing methods typically use a combination of global and local representations (ie, multi-scale features) to achieve superior performance. However, most of them adopt simple linear fusion of multi-scale features, and neglect their possibly complex relationship and interaction. In contrast, humans typically first form a global impression to locate important regions and then focus on local details in those regions. We therefore propose a top-down approach that uses high-level semantics to guide the IQA network to focus on semantically important local distortion regions, named as TOPIQ. Our approach to IQA involves the design of a heuristic coarse-to-fine network (CFANet) that leverages multi-scale features and progressively propagates multi-level semantic information to low-level representations in a top-down manner. A key component of our approach is the proposed cross-scale attention mechanism, which calculates attention maps for lower level features guided by higher level features. This mechanism emphasizes active semantic regions for low-level distortions, thereby improving performance. CFANet can be used for both Full-Reference (FR) and No-Reference (NR) IQA. We use ResNet50 as its backbone and demonstrate that CFANet achieves better or competitive performance on most public FR and NR benchmarks compared with state-of-the-art methods based on vision transformers, while being much more efficient (with only ~13% FLOPS of the current best FR method). Codes are released at urlhttps://github.com/chaofengc/IQA-PyTorch.