mlsanityData to 7 Oct 2026

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

arXiv 2308.03060 ↗First posted 6 Aug 2023cs.CVcited by 220

Not on the map. Why?

Cited by 43 in Diffusion models, but placed by its own abstract, which didn’t fit.

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.

Key facts. Cited by 220 papers in the map (data through 7 Oct 2026). Builds on 40 of its 89 references that are in the map. First posted on arXiv 6 Aug 2023.

Builds on

40 of 89 references.

References · 40

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  7. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  8. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  9. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  10. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 514
  11. 2017NIMA: Neural Image Assessmentcited by 387
  12. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 351
28 more
  1. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 301
  2. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 276
  3. 2016Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessmentcited by 224
  4. 2019From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Qualitycited by 221
  5. 2015Massive Online Crowdsourced Study of Subjective and Objective Picture Qualitycited by 208
  6. 2013Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Indexcited by 193
  7. 2020PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restorationcited by 177
  8. 2021No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistencycited by 165
  9. 2018PieAPP: Perceptual Image-Error Assessment through Pairwise Preferencecited by 158
  10. 2018The 2018 PIRM Challenge on Perceptual Image Super-resolutioncited by 155
  11. 2017RankIQA: Learning from Rankings for No-reference Image Quality Assessmentcited by 150
  12. 2020MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessmentcited by 144
  13. 2016Learning a No-Reference Quality Metric for Single-Image Super-Resolutioncited by 143
  14. 2023AGIQA-3K: An Open Database for AI-Generated Image Quality Assessmentcited by 142
  15. 2020Cross-domain Object Detection through Coarse-to-Fine Feature Adaptationcited by 82
  16. 2020Transformer for Image Quality Assessmentcited by 76
  17. 2021Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Trainingcited by 71
  18. 2022Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Networkcited by 57
  19. 2021Perceptual Image Quality Assessment with Transformerscited by 54
  20. 2019Effective Aesthetics Prediction with Multi-level Spatially Pooled Featurescited by 52
  21. 2018Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learningcited by 49
  22. 2021Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessmentcited by 41
  23. 2022NTIRE 2022 Challenge on Perceptual Image Quality Assessmentcited by 41
  24. 2018Coarse-to-fine Semantic Segmentation from Image-level Labelscited by 28
  25. 2021NTIRE 2021 Challenge on Perceptual Image Quality Assessmentcited by 18
  26. 2021Towards Top-Down Just Noticeable Difference Estimation of Natural Imagescited by 15
  27. 2022Distilling Knowledge from Object Classification to Aesthetics Assessmentcited by 12
  28. 2019Theme-Aware Aesthetic Distribution Prediction With Full-Resolution Photographscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 56; 2025: 83; 2026: 78.

220 papers.

Sort:

By area:

  1. 2023Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Modelscited by 152
  2. 2025HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformercited by 131
  3. 2024Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Comparecited by 66
  4. 2024A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessmentcited by 43
  5. 2025One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillationcited by 40
  6. 2025Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumptioncited by 34
  7. 2024AIGIQA-20K: A Large Database for AI-Generated Image Quality Assessmentcited by 33
  8. 2024GoodDrag: Towards Good Practices for Drag Editing with Diffusion Modelscited by 33
  9. 2023Enhancing Diffusion Models with Text-Encoder Reinforcement Learningcited by 30
  10. 2024R-Bench: Are your Large Multimodal Model Robust to Real-world Corruptions?cited by 29
  11. 2026HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformercited by 29
  12. 2025Compressed Image Generation with Denoising Diffusion Codebook Modelscited by 24
38 more
  1. 2025Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Modelscited by 24
  2. 2025Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Trainingcited by 21
  3. 2024SSUMamba: Spatial-Spectral Selective State Space Model for Hyperspectral Image Denoisingcited by 20
  4. 2024Face Anonymization Made Simplecited by 18
  5. 2024Omni-ID: Holistic Identity Representation Designed for Generative Taskscited by 18
  6. 2025Iterative Predictor-Critic Code Decoding for Real-World Image Dehazingcited by 16
  7. 2024Video Quality Assessment: A Comprehensive Surveycited by 15
  8. 2025TurboFill: Adapting Few-step Text-to-image Model for Fast Image Inpaintingcited by 15
  9. 2025MIRA: Multimodal Iterative Reasoning Agent for Image Editingcited by 15
  10. 2024PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Promptscited by 14
  11. 2024Benchmarking Multi-dimensional AIGC Video Quality Assessment: A Dataset and Unified Modelcited by 13
  12. 2024Exploring Rich Subjective Quality Information for Image Quality Assessment in the Wildcited by 13
  13. 2024Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEscited by 13
  14. 2024SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuningcited by 13
  15. 2024Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessmentcited by 12
  16. 2025Image Quality Assessment: From Human to Machine Preferencecited by 12
  17. 2025MoA-VR: A Mixture-of-Agents System Towards All-in-One Video Restorationcited by 12
  18. 2025KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perceptioncited by 11
  19. 2025KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolutioncited by 11
  20. 2024AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion modelscited by 10
  21. 2024Assessing UHD Image Quality from Aesthetics, Distortions, and Saliencycited by 9
  22. 2025Probability Density Geodesics in Image Diffusion Latent Spacecited by 9
  23. 2024Imperceptible Protection against Style Imitation from Diffusion Modelscited by 8
  24. 2024S4Fusion: Saliency-aware Selective State Space Model for Infrared Visible Image Fusioncited by 8
  25. 2024Conti-Fuse: A Novel Continuous Decomposition-based Fusion Framework for Infrared and Visible Imagescited by 8
  26. 2024AdaDiffSR: Adaptive Region-aware Dynamic Acceleration Diffusion Model for Real-World Image Super-Resolutioncited by 8
  27. 2025Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restorationcited by 8
  28. 2024AIM 2024 Challenge on Compressed Video Quality Assessment: Methods and Resultscited by 7
  29. 2025HarmonyIQA: Pioneering Benchmark and Model for Image Harmonization Quality Assessmentcited by 7
  30. 2025Augmenting Perceptual Super-Resolution via Image Quality Predictorscited by 7
  31. 2025TinySR: Pruning Diffusion for Real-World Image Super-Resolutioncited by 7
  32. 2025Nested Unfolding Network for Real-World Concealed Object Segmentationcited by 7
  33. 2024Diffusion Model Based Visual Compensation Guidance and Visual Difference Analysis for No-Reference Image Quality Assessmentcited by 6
  34. 2024CMC-Bench: Towards a New Paradigm of Visual Signal Compressioncited by 6
  35. 2024Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Modelscited by 6
  36. 2025Text-Visual Semantic Constrained AI-Generated Image Quality Assessmentcited by 6
  37. 2025Time-Aware One Step Diffusion Network for Real-World Image Super-Resolutioncited by 6
  38. 2024Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metricscited by 5

50 most cited of 220 All 220 (JSON)