mlsanityData to 7 Oct 2026

Blind Image Decomposition

arXiv 2108.11364 ↗First posted 25 Aug 2021cs.CV eess.IVcited by 18

Not on the map. Why?

Abstract (arXiv)

We propose and study a novel task named Blind Image Decomposition (BID), which requires separating a superimposed image into constituent underlying images in a blind setting, that is, both the source components involved in mixing as well as the mixing mechanism are unknown. For example, rain may consist of multiple components, such as rain streaks, raindrops, snow, and haze. Rainy images can be treated as an arbitrary combination of these components, some of them or all of them. How to decompose superimposed images, like rainy images, into distinct source components is a crucial step toward real-world vision systems. To facilitate research on this new task, we construct multiple benchmark datasets, including mixed image decomposition across multiple domains, real-scenario deraining, and joint shadow/reflection/watermark removal. Moreover, we propose a simple yet general Blind Image Decomposition Network (BIDeN) to serve as a strong baseline for future work. Experimental results demonstrate the tenability of our benchmarks and the effectiveness of BIDeN.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 50 of its 102 references that are in the map. First posted on arXiv 25 Aug 2021.

Builds on

50 of 102 references.

References · 50

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  7. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  8. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  9. 2017Deep Image Priorcited by 1,097
  10. 2016Least Squares Generative Adversarial Networkscited by 1,000
  11. 2021Multi-Stage Progressive Image Restorationcited by 813
  12. 2018Self-Attention Generative Adversarial Networkscited by 809
38 more
  1. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  2. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 401
  3. 2016Deep Joint Rain Detection and Removal from a Single Imagecited by 351
  4. 2018Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Derainingcited by 205
  5. 2017Attentive Generative Adversarial Network for Raindrop Removal from a Single Imagecited by 204
  6. 2017DesnowNet: Context-Aware Deep Network for Snow Removalcited by 200
  7. 2017Image De-raining Using a Conditional Generative Adversarial Networkcited by 197
  8. 2020Real-Time High-Resolution Background Mattingcited by 172
  9. 2017Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removalcited by 160
  10. 2020A Model-driven Deep Neural Network for Single Image Rain Removalcited by 125
  11. 2018"Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priorscited by 114
  12. 2019Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GANcited by 102
  13. 2018Single Image Reflection Separation with Perceptual Lossescited by 98
  14. 2019Shadow Removal via Shadow Image Decompositioncited by 96
  15. 2020Deep Visual Domain Adaptationcited by 91
  16. 2019Single Image Deraining: A Comprehensive Benchmark Analysiscited by 84
  17. 2021Auto-Exposure Fusion for Single-Image Shadow Removalcited by 78
  18. 2021Dual Contrastive Learning for Unsupervised Image-to-Image Translationcited by 65
  19. 2017A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothingcited by 60
  20. 2019Single Image Reflection Removal through Cascaded Refinementcited by 58
  21. 2017Direction-aware Spatial Context Features for Shadow Detectioncited by 56
  22. 2019ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removalcited by 51
  23. 2020How to Train Neural Networks for Flare Removalcited by 50
  24. 2021CANet: A Context-Aware Network for Shadow Removalcited by 47
  25. 2019REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Datacited by 40
  26. 2020WDNet: Watermark-Decomposition Network for Visible Watermark Removalcited by 37
  27. 2018Deep Object Co-Segmentationcited by 35
  28. 2020Source Separation with Deep Generative Priorscited by 35
  29. 2021Dual Attention-in-Attention Model for Joint Rain Streak and Raindrop Removalcited by 24
  30. 2018The Visual Centrifuge: Model-Free Layered Video Representationscited by 23
  31. 2019I Can See Clearly Now : Image Restoration via De-Rainingcited by 23
  32. 2020Learning to See Through Obstructions with Layered Decompositioncited by 20
  33. 2021Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Priorcited by 18
  34. 2021Underwater Image Restoration via Contrastive Learning and a Real-world Datasetcited by 15
  35. 2019Single-Channel Signal Separation and Deconvolution with Generative Adversarial Networkscited by 9
  36. 2018Stereo Computation for a Single Mixture Imagecited by 6
  37. 2018Neural separation of observed and unobserved distributionscited by 6
  38. 2018Accurate and efficient video de-fencing using convolutional neural networks and temporal informationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

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

18 papers.

Sort:

By area:

  1. 2024OneRestore: A Universal Restoration Framework for Composite Degradationcited by 91
  2. 2024A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trendscited by 58
  3. 2022You Only Cut Once: Boosting Data Augmentation with a Single Cutcited by 22
  4. 2022Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learningcited by 18
  5. 2022Efficient Mirror Detection via Multi-level Heterogeneous Learningcited by 13
  6. 2023WM-MoE: Weather-aware Multi-scale Mixture-of-Experts for Blind Adverse Weather Removalcited by 11
  7. 2022CropMix: Sampling a Rich Input Distribution via Multi-Scale Croppingcited by 8
  8. 2024Chain-of-Restoration: Multi-Task Image Restoration Models are Zero-Shot Step-by-Step Universal Image Restorerscited by 4
  9. 2025Instruct2See: Learning to Remove Any Obstructions Across Distributionscited by 3
  10. 2025PhyDAE: Physics-Guided Degradation-Adaptive Experts for All-in-One Remote Sensing Image Restorationcited by 3
  11. 2023MetaWeather: Few-Shot Weather-Degraded Image Restorationcited by 2
  12. 2024Strong and Controllable Blind Image Decompositioncited by 2
6 more
  1. 2025Clear Nights Ahead: Towards Multi-Weather Nighttime Image Restorationcited by 2
  2. 2024Joint Conditional Diffusion Model for Image Restoration with Mixed Degradationscited by 1
  3. 2022Asymmetric Dual-Decoder U-Net for Joint Rain and Haze Removalcited by 0
  4. 2025Removing Multiple Hybrid Adverse Weather in Video via a Unified Modelcited by 0
  5. 2026Unifying Physically-Informed Weather Priors in A Single Model for Image Restoration Across Multiple Adverse Weather Conditionscited by 0
  6. 2026What to Remove, What to Preserve: Dual-Ambiguity Rectification for All-in-One Image Restorationcited by 0