mlsanityData to 7 Oct 2026

MUSIQ: Multi-scale Image Quality Transformer

arXiv 2108.05997 ↗First posted 12 Aug 2021cs.CVcited by 1,058

Not on the map. Why?

Cited by 356 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Image quality assessment (IQA) is an important research topic for understanding and improving visual experience. The current state-of-the-art IQA methods are based on convolutional neural networks (CNNs). The performance of CNN-based models is often compromised by the fixed shape constraint in batch training. To accommodate this, the input images are usually resized and cropped to a fixed shape, causing image quality degradation. To address this, we design a multi-scale image quality Transformer (MUSIQ) to process native resolution images with varying sizes and aspect ratios. With a multi-scale image representation, our proposed method can capture image quality at different granularities. Furthermore, a novel hash-based 2D spatial embedding and a scale embedding is proposed to support the positional embedding in the multi-scale representation. Experimental results verify that our method can achieve state-of-the-art performance on multiple large scale IQA datasets such as PaQ-2-PiQ, SPAQ and KonIQ-10k.

Key facts. Cited by 1,058 papers in the map (data through 7 Oct 2026). Builds on 31 of its 53 references that are in the map. First posted on arXiv 12 Aug 2021.

Builds on

31 of 53 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  8. 2020End-to-End Object Detection with Transformerscited by 7,384
  9. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  10. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  11. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  12. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
19 more
  1. 2018Self-Attention with Relative Position Representationscited by 1,112
  2. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  3. 2020Pre-Trained Image Processing Transformercited by 891
  4. 2017Convolutional Sequence to Sequence Learningcited by 550
  5. 2017NIMA: Neural Image Assessmentcited by 387
  6. 2019Attention Augmented Convolutional Networkscited by 363
  7. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 351
  8. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 301
  9. 2016Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessmentcited by 224
  10. 2019From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Qualitycited by 221
  11. 2020MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessmentcited by 144
  12. 2016Photo Aesthetics Ranking Network with Attributes and Content Adaptationcited by 122
  13. 2020Transformer for Image Quality Assessmentcited by 76
  14. 2016Perceptual Quality Prediction on Authentically Distorted Images Using a Bag of Features Approachcited by 71
  15. 2019Effective Aesthetics Prediction with Multi-level Spatially Pooled Featurescited by 52
  16. 2017A-Lamp: Adaptive Layout-Aware Multi-Patch Deep Convolutional Neural Network for Photo Aesthetic Assessmentcited by 28
  17. 2017A Probabilistic Quality Representation Approach to Deep Blind Image Quality Predictioncited by 28
  18. 2020Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessmentcited by 28
  19. 2017A deep architecture for unified aesthetic predictioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 26; 2023: 89; 2024: 206; 2025: 361; 2026: 375.

1,058 papers.

Sort:

By area:

  1. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  2. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  3. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  4. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 514
  5. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 489
  6. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  7. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  8. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 360
  9. 2024OminiControl: Minimal and Universal Control for Diffusion Transformercited by 334
  10. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 311
  11. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 281
  12. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 276
38 more
  1. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 255
  2. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 251
  3. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 243
  4. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 235
  5. 2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 230
  6. 2023TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessmentcited by 220
  7. 2025SkyReels-V2: Infinite-length Film Generative Modelcited by 218
  8. 2024Taming Rectified Flow for Inversion and Editingcited by 200
  9. 2023FreeU: Free Lunch in Diffusion U-Netcited by 195
  10. 2022FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Samplingcited by 179
  11. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 165
  12. 2023Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Modelscited by 152
  13. 2024MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captionscited by 144
  14. 2025WorldScore: A Unified Evaluation Benchmark for World Generationcited by 143
  15. 2023Rich Human Feedback for Text-to-Image Generationcited by 139
  16. 2025Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distributioncited by 139
  17. 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolutioncited by 131
  18. 2025Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Modelscited by 126
  19. 2025Emu3.5: Native Multimodal Models are World Learnerscited by 119
  20. 2023Iterative Prompt Learning for Unsupervised Backlit Image Enhancementcited by 107
  21. 2023Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Modelscited by 104
  22. 2024VideoDPO: Omni-Preference Alignment for Video Diffusion Generationcited by 102
  23. 2023AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusioncited by 98
  24. 2023Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wildcited by 97
  25. 2022LEDNet: Joint Low-light Enhancement and Deblurring in the Darkcited by 95
  26. 2024Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approachcited by 93
  27. 2025Q-Insight: Understanding Image Quality via Visual Reinforcement Learningcited by 93
  28. 2025LongCat-Image Technical Reportcited by 92
  29. 2024LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generationcited by 91
  30. 2023ARNIQA: Learning Distortion Manifold for Image Quality Assessmentcited by 87
  31. 2024FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attentioncited by 87
  32. 2023Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancementcited by 86
  33. 2024Arbitrary-steps Image Super-resolution via Diffusion Inversioncited by 85
  34. 2024T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedbackcited by 84
  35. 2024Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusioncited by 83
  36. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 83
  37. 2025Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understandingcited by 83
  38. 2025VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rankcited by 77

50 most cited of 1,058 All 1,058 (JSON)