mlsanityData to 7 Oct 2026

Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution

arXiv 2208.03324 ↗First posted 5 Aug 2022eess.IV cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

In image super-resolution, both pixel-wise accuracy and perceptual fidelity are desirable. However, most deep learning methods only achieve high performance in one aspect due to the perception-distortion trade-off, and works that successfully balance the trade-off rely on fusing results from separately trained models with ad-hoc post-processing. In this paper, we propose a novel super-resolution model with a low-frequency constraint (LFc-SR), which balances the objective and perceptual quality through a single model and yields super-resolved images with high PSNR and perceptual scores. We further introduce an ADMM-based alternating optimization method for the non-trivial learning of the constrained model. Experiments showed that our method, without cumbersome post-processing procedures, achieved the state-of-the-art performance. The code is available at https://github.com/Yuehan717/PDASR.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 37 of its 56 references that are in the map. First posted on arXiv 5 Aug 2022.

Builds on

37 of 56 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  5. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  6. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  7. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  8. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  9. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  10. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  11. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  12. 2017The Perception-Distortion Tradeoffcited by 582
25 more
  1. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 326
  2. 2015Deeply-Recursive Convolutional Network for Image Super-Resolutioncited by 317
  3. 2020Single Image Super-Resolution via a Holistic Attention Networkcited by 265
  4. 2018Multi-level Wavelet-CNN for Image Restorationcited by 184
  5. 2019RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolutioncited by 145
  6. 2016Learning a No-Reference Quality Metric for Single-Image Super-Resolutioncited by 143
  7. 2018The Contextual Loss for Image Transformation with Non-Aligned Datacited by 135
  8. 2018A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multiplierscited by 118
  9. 2020Structure-Preserving Super Resolution with Gradient Guidancecited by 116
  10. 2017Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMMcited by 60
  11. 2021A Theory of the Distortion-Perception Tradeoff in Wasserstein Spacecited by 52
  12. 2021Single Image Depth Prediction with Wavelet Decompositioncited by 34
  13. 2019Wavelet Domain Style Transfer for an Effective Perception-distortion Tradeoff in Single Image Super-Resolutioncited by 30
  14. 2019CFSNet: Toward a Controllable Feature Space for Image Restorationcited by 25
  15. 2018Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolutioncited by 24
  16. 2018Maintaining Natural Image Statistics with the Contextual Losscited by 19
  17. 2018Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Networkcited by 16
  18. 2018Dynamic-Net: Tuning the Objective Without Re-training for Synthesis Taskscited by 9
  19. 2018An ADMM-Based Universal Framework for Adversarial Attacks on Deep Neural Networkscited by 6
  20. 2015A Simple Effective Heuristic for Embedded Mixed-Integer Quadratic Programmingcited by 5
  21. 2016Alternating Direction Method of Multipliers for Sparse Convolutional Neural Networkscited by 4
  22. 2018Multi-Scale Recursive and Perception-Distortion Controllable Image Super-Resolutioncited by 4
  23. 2020Smoother Network Tuning and Interpolation for Continuous-level Image Processingcited by 3
  24. 2017Deep Spatio-temporal Manifold Network for Action Recognitioncited by 1
  25. 2020WDN: A Wide and Deep Network to Divide-and-Conquer Image Super-resolutioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 9; 2025: 3; 2026: 4.

19 papers.

Sort:

By area:

  1. 2024Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approachcited by 93
  2. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 83
  3. 2024AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillationcited by 66
  4. 2024Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifactscited by 16
  5. 2023Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolutioncited by 15
  6. 2023Perception-Distortion Balanced Super-Resolution: A Multi-Objective Optimization Perspectivecited by 11
  7. 2024Training Transformer Models by Wavelet Losses Improves Quantitative and Visual Performance in Single Image Super-Resolutioncited by 10
  8. 2023Reconstruct-and-Generate Diffusion Model for Detail-Preserving Image Denoisingcited by 5
  9. 2024Auto-Encoded Supervision for Perceptual Image Super-Resolutioncited by 4
  10. 2024XYScanNet: A State Space Model for Single Image Deblurringcited by 4
  11. 2024Pairwise Distance Distillation for Unsupervised Real-World Image Super-Resolutioncited by 2
  12. 2024Trustworthy SR: Resolving Ambiguity in Image Super-resolution via Diffusion Models and Human Feedbackcited by 1
7 more
  1. 2025Diffusion Transformer meets Multi-level Wavelet Spectrum for Single Image Super-Resolutioncited by 1
  2. 2025Image-Difficulty-Aware Evaluation of Super-Resolution Modelscited by 0
  3. 2025HDW-SR: High-Frequency Guided Diffusion Model based on Wavelet Decomposition for Image Super-Resolutioncited by 0
  4. 2026Revisiting the Perception-Distortion Trade-off with Spatial-Semantic Guided Super-Resolutioncited by 0
  5. 2026AlloSR2: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flowscited by 0
  6. 2026Noise-Started One-Step Real-World Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinementcited by 0
  7. 2026ScaleResfusion: Residual Rectified Flow based on Residual Vector Fieldcited by 0