mlsanityData to 7 Oct 2026

Towards Flexible Blind JPEG Artifacts Removal

arXiv 2109.14573 ↗First posted 29 Sep 2021eess.IV cs.CVcited by 76

Not on the map. Why?

Abstract (arXiv)

Training a single deep blind model to handle different quality factors for JPEG image artifacts removal has been attracting considerable attention due to its convenience for practical usage. However, existing deep blind methods usually directly reconstruct the image without predicting the quality factor, thus lacking the flexibility to control the output as the non-blind methods. To remedy this problem, in this paper, we propose a flexible blind convolutional neural network, namely FBCNN, that can predict the adjustable quality factor to control the trade-off between artifacts removal and details preservation. Specifically, FBCNN decouples the quality factor from the JPEG image via a decoupler module and then embeds the predicted quality factor into the subsequent reconstructor module through a quality factor attention block for flexible control. Besides, we find existing methods are prone to fail on non-aligned double JPEG images even with only a one-pixel shift, and we thus propose a double JPEG degradation model to augment the training data. Extensive experiments on single JPEG images, more general double JPEG images, and real-world JPEG images demonstrate that our proposed FBCNN achieves favorable performance against state-of-the-art methods in terms of both quantitative metrics and visual quality.

Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). Builds on 28 of its 57 references that are in the map. First posted on arXiv 29 Sep 2021.

Builds on

28 of 57 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  6. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  7. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  8. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  9. 2016Generative Adversarial Text to Image Synthesiscited by 735
  10. 2017AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkscited by 664
  11. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  12. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
16 more
  1. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  2. 2018Toward Convolutional Blind Denoising of Real Photographscited by 274
  3. 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 241
  4. 2019Residual Non-local Attention Networks for Image Restorationcited by 236
  5. 2017Learning a Single Convolutional Super-Resolution Network for Multiple Degradationscited by 227
  6. 2015Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restorationcited by 194
  7. 2019Controllable Text-to-Image Generationcited by 187
  8. 2018Multi-level Wavelet-CNN for Image Restorationcited by 184
  9. 2015Compression Artifacts Reduction by a Deep Convolutional Networkcited by 136
  10. 2019STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editingcited by 119
  11. 2020Quantization Guided JPEG Artifact Correctioncited by 57
  12. 2016CAS-CNN: A Deep Convolutional Neural Network for Image Compression Artifact Suppressioncited by 33
  13. 2019CFSNet: Toward a Controllable Feature Space for Image Restorationcited by 25
  14. 2017Aligned and Non-Aligned Double JPEG Detection Using Convolutional Neural Networkscited by 22
  15. 2018DMCNN: Dual-Domain Multi-Scale Convolutional Neural Network for Compression Artifacts Removalcited by 20
  16. 2018Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reductioncited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 14; 2023: 14; 2024: 20; 2025: 20; 2026: 8.

76 papers.

Sort:

By area:

  1. 2023Efficient and Explicit Modelling of Image Hierarchies for Image Restorationcited by 145
  2. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  3. 2022Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesiscited by 85
  4. 2022Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restorationcited by 72
  5. 2023HAT: Hybrid Attention Transformer for Image Restorationcited by 64
  6. 2024Lightweight Adaptive Feature De-drifting for Compressed Image Classificationcited by 46
  7. 2022JPEG Artifact Correction using Denoising Diffusion Restoration Modelscited by 45
  8. 2024RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Modelscited by 41
  9. 2024An Intelligent Agentic System for Complex Image Restoration Problemscited by 41
  10. 2024Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Datasetcited by 38
  11. 2022MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolutioncited by 33
  12. 2025Visual-Instructed Degradation Diffusion for All-in-One Image Restorationcited by 26
38 more
  1. 2022Enriched CNN-Transformer Feature Aggregation Networks for Super-Resolutioncited by 22
  2. 2023A Unified Conditional Framework for Diffusion-based Image Restorationcited by 22
  3. 2024Revisiting Tampered Scene Text Detection in the Era of Generative AIcited by 21
  4. 2022AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Resultscited by 20
  5. 2024PromptCIR: Blind Compressed Image Restoration with Prompt Learningcited by 20
  6. 2025Multi-Agent Image Restorationcited by 19
  7. 2023SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-Resolutioncited by 18
  8. 2024Ultra Inertial Poser: Scalable Motion Capture and Tracking from Sparse Inertial Sensors and Ultra-Wideband Rangingcited by 18
  9. 2022From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolutioncited by 15
  10. 2022DriftRec: Adapting diffusion models to blind JPEG restorationcited by 15
  11. 2023Dynamic Path-Controllable Deep Unfolding Network for Compressive Sensingcited by 15
  12. 2024Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restorationcited by 15
  13. 2024Sharing Key Semantics in Transformer Makes Efficient Image Restorationcited by 14
  14. 2025Hybrid Agents for Image Restorationcited by 14
  15. 2025Compression-Aware One-Step Diffusion Model for JPEG Artifact Removalcited by 13
  16. 2023Synthesizing Realistic Image Restoration Training Pairs: A Diffusion Approachcited by 11
  17. 2023Learning a Practical SDR-to-HDRTV Up-conversion using New Dataset and Degradation Modelscited by 11
  18. 2025Reversing Flow for Image Restorationcited by 10
  19. 2022High-Perceptual Quality JPEG Decoding via Posterior Samplingcited by 8
  20. 2024UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Promptcited by 8
  21. 2024JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficientscited by 7
  22. 2025Lightweight Medical Image Restoration via Integrating Reliable Lesion-Semantic Driven Priorcited by 7
  23. 2022LHDR: HDR Reconstruction for Legacy Content using a Lightweight DNNcited by 6
  24. 2023Restore Anything Pipeline: Segment Anything Meets Image Restorationcited by 6
  25. 2022Learning Parallax Transformer Network for Stereo Image JPEG Artifacts Removalcited by 5
  26. 2022Practical exposure correction via compensationcited by 5
  27. 2024Sensitivity Decouple Learning for Image Compression Artifacts Reductioncited by 5
  28. 2023Tunable Convolutions with Parametric Multi-Loss Optimizationcited by 4
  29. 2023Dequantization and Color Transfer with Diffusion Modelscited by 4
  30. 2025FDG-Diff: Frequency-Domain-Guided Diffusion Framework for Compressed Hazy Image Restorationcited by 4
  31. 2025Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedbackcited by 4
  32. 2023Dual-layer Image Compression via Adaptive Downsampling and Spatially Varying Upconversioncited by 3
  33. 2023JPEG Quantized Coefficient Recovery via DCT Domain Spatial-Frequential Transformercited by 3
  34. 2024Key-Graph Transformer for Image Restorationcited by 3
  35. 2024OAPT: Offset-Aware Partition Transformer for Double JPEG Artifacts Removalcited by 3
  36. 2025PosDiffAE: Position-aware Diffusion Auto-encoder For High-Resolution Brain Tissue Classification Incorporating Artifact Restorationcited by 3
  37. 2025Webly-Supervised Image Manipulation Localization via Category-Aware Auto-Annotationcited by 3
  38. 2026ATD: Improved Transformer with Adaptive Token Dictionary for Image Restorationcited by 3

50 most cited of 76 All 76 (JSON)