mlsanityData to 14 Oct 2026

No-Reference Image Quality Assessment by Hallucinating Pristine Features

arXiv 2108.04165 ↗First posted 9 Aug 2021eess.IV cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a no-reference (NR) image quality assessment (IQA) method via feature level pseudo-reference (PR) hallucination. The proposed quality assessment framework is grounded on the prior models of natural image statistical behaviors and rooted in the view that the perceptually meaningful features could be well exploited to characterize the visual quality. Herein, the PR features from the distorted images are learned by a mutual learning scheme with the pristine reference as the supervision, and the discriminative characteristics of PR features are further ensured with the triplet constraints. Given a distorted image for quality inference, the feature level disentanglement is performed with an invertible neural layer for final quality prediction, leading to the PR and the corresponding distortion features for comparison. The effectiveness of our proposed method is demonstrated on four popular IQA databases, and superior performance on cross-database evaluation also reveals the high generalization capability of our method. The implementation of our method is publicly available on https://github.com/Baoliang93/FPR.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 29 of its 105 references that are in the map. First posted on arXiv 9 Aug 2021.

Builds on

29 of 105 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  4. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  5. 2016Density estimation using Real NVPcited by 2,042
  6. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  7. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  8. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 657
  9. 2017Deep Mutual Learningcited by 628
  10. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 408
  11. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 302
  12. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 242
17 more
  1. 2016Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessmentcited by 225
  2. 2017RankIQA: Learning from Rankings for No-reference Image Quality Assessmentcited by 151
  3. 2016Dual Learning for Machine Translationcited by 148
  4. 2020Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wildcited by 134
  5. 2019dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairscited by 73
  6. 2020Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Trainingcited by 72
  7. 2016Perceptual Quality Prediction on Authentically Distorted Images Using a Bag of Features Approachcited by 71
  8. 2020Norm-in-Norm Loss with Faster Convergence and Better Performance for Image Quality Assessmentcited by 54
  9. 2018Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learningcited by 49
  10. 2017Quality Aware Network for Set to Set Recognitioncited by 36
  11. 2016On the Use of Deep Learning for Blind Image Quality Assessmentcited by 34
  12. 2019Subjective and Objective De-raining Quality Assessment Towards Authentic Rain Imagecited by 18
  13. 2020No-reference Screen Content Image Quality Assessment with Unsupervised Domain Adaptationcited by 17
  14. 2017A Perceptually Weighted Rank Correlation Indicator for Objective Image Quality Assessmentcited by 13
  15. 2017Cooperative Learning with Visual Attributescited by 8
  16. 2021Self-supervised Low Light Image Enhancement and Denoisingcited by 8
  17. 2020Referenceless Rate-Distortion Modeling with Learning from Bitstream and Pixel Featurescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 2; 2024: 4; 2025: 4; 2026: 1.

16 papers.

Sort:

By area:

  1. 2024Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Comparecited by 66
  2. 2022DeepWSD: Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Spacecited by 20
  3. 2024PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wildcited by 17
  4. 2024Video Quality Assessment: A Comprehensive Surveycited by 15
  5. 2023Comparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attackscited by 14
  6. 2025AGHI-QA: A Subjective-Aligned Dataset and Metric for AI-Generated Human Imagescited by 13
  7. 2022MSTRIQ: No Reference Image Quality Assessment Based on Swin Transformer with Multi-Stage Fusioncited by 10
  8. 2024Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metricscited by 5
  9. 2023You Only Train Once: A Unified Framework for Both Full-Reference and No-Reference Image Quality Assessmentcited by 4
  10. 2022Deep Feature Statistics Mapping for Generalized Screen Content Image Quality Assessmentcited by 3
  11. 2022The Loop Game: Quality Assessment and Optimization for Low-Light Image Enhancementcited by 2
  12. 2022Learning from Mixed Datasets: A Monotonic Image Quality Assessment Modelcited by 2
4 more
  1. 2025Neural Atlas Graphs for Dynamic Scene Decomposition and Editingcited by 2
  2. 2025Plug In, Grade Right: Psychology-Inspired AGIQAcited by 2
  3. 2026From Global to Granular: Revealing IQA Model Performance via Correlation Surfacecited by 2
  4. 2025No-reference Quality Assessment of Contrast-distorted Images using Contrast-enhanced Pseudo Referencecited by 0