mlsanityData to 7 Oct 2026

Locally Adaptive Structure and Texture Similarity for Image Quality Assessment

arXiv 2110.08521 ↗First posted 16 Oct 2021eess.IV cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

The latest advances in full-reference image quality assessment (IQA) involve unifying structure and texture similarity based on deep representations. The resulting Deep Image Structure and Texture Similarity (DISTS) metric, however, makes rather global quality measurements, ignoring the fact that natural photographic images are locally structured and textured across space and scale. In this paper, we describe a locally adaptive structure and texture similarity index for full-reference IQA, which we term A-DISTS. Specifically, we rely on a single statistical feature, namely the dispersion index, to localize texture regions at different scales. The estimated probability (of one patch being texture) is in turn used to adaptively pool local structure and texture measurements. The resulting A-DISTS is adapted to local image content, and is free of expensive human perceptual scores for supervised training. We demonstrate the advantages of A-DISTS in terms of correlation with human data on ten IQA databases and optimization of single image super-resolution methods.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 15 of its 42 references that are in the map. First posted on arXiv 16 Oct 2021.

Builds on

15 of 42 references.

References · 15

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  4. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  5. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  6. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  7. 2020Deep Unfolding Network for Image Super-Resolutioncited by 253
  8. 2016Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessmentcited by 224
  9. 2013Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Indexcited by 193
  10. 2018PieAPP: Perceptual Image-Error Assessment through Pairwise Preferencecited by 158
  11. 2019RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolutioncited by 145
  12. 2016Learning a No-Reference Quality Metric for Single-Image Super-Resolutioncited by 143
3 more
  1. 2021Quantifying Visual Image Quality: A Bayesian Viewcited by 20
  2. 2015Geodesics of learned representationscited by 14
  3. 2021Debiased Subjective Assessment of Real-World Image Enhancementcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 4; 2024: 9; 2025: 8; 2026: 7.

32 papers.

Sort:

By area:

  1. 2025Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distributioncited by 139
  2. 2023Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Modelscited by 104
  3. 2025Q-Insight: Understanding Image Quality via Visual Reinforcement Learningcited by 93
  4. 2024Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Datasetcited by 38
  5. 2025Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumptioncited by 34
  6. 2022DeepWSD: Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Spacecited by 19
  7. 2024Video Quality Assessment: A Comprehensive Surveycited by 15
  8. 2025The Power of Context: How Multimodality Improves Image Super-Resolutioncited by 15
  9. 2024Multiscale Sliced Wasserstein Distances as Perceptual Color Difference Measurescited by 14
  10. 2022DeepDC: Deep Distance Correlation as a Perceptual Image Quality Evaluatorcited by 10
  11. 2022StyleAM: Perception-Oriented Unsupervised Domain Adaption for Non-reference Image Quality Assessmentcited by 9
  12. 2024Arbitrary-Scale Video Super-Resolution with Structural and Textural Priorscited by 9
20 more
  1. 2023Attacking Perceptual Similarity Metricscited by 8
  2. 2026X2HDR: HDR Image Generation in a Perceptually Uniform Spacecited by 7
  3. 2024Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approachcited by 6
  4. 2022Perceptual Quality Assessment for Fine-Grained Compressed Imagescited by 5
  5. 2023Towards a Perceptual Evaluation Framework for Lighting Estimationcited by 5
  6. 2024Deep Shape-Texture Statistics for Completely Blind Image Quality Evaluationcited by 5
  7. 2025UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancementcited by 5
  8. 2024Image Quality Assessment: Investigating Causal Perceptual Effects with Abductive Counterfactual Inferencecited by 4
  9. 2025MILO: A Lightweight Perceptual Quality Metric for Image and Latent-Space Optimizationcited by 3
  10. 2023Enhancing image quality prediction with self-supervised visual maskingcited by 2
  11. 2024Learned HDR Image Compression for Perceptually Optimal Storage and Displaycited by 2
  12. 2025DeQA-Doc: Adapting DeQA-Score to Document Image Quality Assessmentcited by 2
  13. 2026How far have we gone in Generative Image Restoration? A study on its capability, limitations and evaluation practicescited by 2
  14. 2026OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolutioncited by 1
  15. 2024Image Quality Assessment: Enhancing Perceptual Exploration and Interpretation with Collaborative Feature Refinement and Hausdorff distancecited by 0
  16. 2025The Unanticipated Asymmetry Between Perceptual Optimization and Assessmentcited by 0
  17. 2026Image Quality Assessment: Exploring Quality Awareness via Memory-driven Distortion Patterns Matchingcited by 0
  18. 2026EvoIQA - Explaining Image Distortions with Evolved White-Box Logiccited by 0
  19. 2026Causal Disentanglement-Inspired Degradation Representation Learning for Full-Reference Image Quality Assessmentcited by 0
  20. 2026From Glance to Scrutiny: Progressive Distortion Reasoning for Fine-Grained Image Quality Assessmentcited by 0