mlsanityData to 7 Oct 2026

Stripformer: Strip Transformer for Fast Image Deblurring

arXiv 2204.04627 ↗First posted 10 Apr 2022cs.CVcited by 139

Not on the map. Why?

Abstract (arXiv)

Images taken in dynamic scenes may contain unwanted motion blur, which significantly degrades visual quality. Such blur causes short- and long-range region-specific smoothing artifacts that are often directional and non-uniform, which is difficult to be removed. Inspired by the current success of transformers on computer vision and image processing tasks, we develop, Stripformer, a transformer-based architecture that constructs intra- and inter-strip tokens to reweight image features in the horizontal and vertical directions to catch blurred patterns with different orientations. It stacks interlaced intra-strip and inter-strip attention layers to reveal blur magnitudes. In addition to detecting region-specific blurred patterns of various orientations and magnitudes, Stripformer is also a token-efficient and parameter-efficient transformer model, demanding much less memory usage and computation cost than the vanilla transformer but works better without relying on tremendous training data. Experimental results show that Stripformer performs favorably against state-of-the-art models in dynamic scene deblurring.

Key facts. Cited by 139 papers in the map (data through 7 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 10 Apr 2022.

Builds on

31 of 45 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2017Squeeze-and-Excitation Networkscited by 4,763
  8. 2017Non-local Neural Networkscited by 2,290
  9. 2021Vision Transformers for Dense Predictioncited by 1,789
  10. 2020Pre-Trained Image Processing Transformercited by 891
  11. 2021Multi-Stage Progressive Image Restorationcited by 813
  12. 2018Self-Attention Generative Adversarial Networkscited by 809
19 more
  1. 2018Image Transformercited by 770
  2. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  3. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  4. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  5. 2021Conditional Positional Encodings for Vision Transformerscited by 402
  6. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 361
  7. 2020Learning Texture Transformer Network for Image Super-Resolutioncited by 346
  8. 2018Scale-recurrent Network for Deep Image Deblurringcited by 332
  9. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 324
  10. 2021Contrastive Learning for Compact Single Image Dehazingcited by 219
  11. 2019Deep Stacked Hierarchical Multi-patch Network for Image Deblurringcited by 205
  12. 2020Deblurring by Realistic Blurringcited by 187
  13. 2020Human-Aware Motion Deblurringcited by 174
  14. 2020Learning Joint Spatial-Temporal Transformations for Video Inpaintingcited by 162
  15. 2015Learning a Convolutional Neural Network for Non-uniform Motion Blur Removalcited by 148
  16. 2020Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurringcited by 119
  17. 2020Strip Pooling: Rethinking Spatial Pooling for Scene Parsingcited by 114
  18. 2019Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Trainingcited by 112
  19. 2021Spatially-Adaptive Image Restoration using Distortion-Guided Networkscited by 77

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 18; 2024: 51; 2025: 44; 2026: 22.

139 papers.

Sort:

By area:

  1. 2022Efficient Frequency Domain-based Transformers for High-Quality Image Deblurringcited by 164
  2. 2023Efficient and Explicit Modelling of Image Hierarchies for Image Restorationcited by 145
  3. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  4. 2024AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulationcited by 108
  5. 2023Hierarchical Integration Diffusion Model for Realistic Image Deblurringcited by 87
  6. 2022Multiscale Structure Guided Diffusion for Image Deblurringcited by 76
  7. 2024DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Modelscited by 60
  8. 2024Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restorationcited by 60
  9. 2023Recursive Generalization Transformer for Image Super-Resolutioncited by 28
  10. 2024FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurringcited by 28
  11. 2024Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecturecited by 28
  12. 2024Efficient Visual State Space Model for Image Deblurringcited by 27
38 more
  1. 2025Visual-Instructed Degradation Diffusion for All-in-One Image Restorationcited by 26
  2. 2024Learning Enriched Features via Selective State Spaces Model for Efficient Image Deblurringcited by 25
  3. 2024AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurringcited by 25
  4. 2023Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurringcited by 24
  5. 2024CU-Mamba: Selective State Space Models with Channel Learning for Image Restorationcited by 24
  6. 2023ParamISP: Learned Forward and Inverse ISPs using Camera Parameterscited by 23
  7. 2024Towards Real-world Event-guided Low-light Video Enhancement and Deblurringcited by 22
  8. 2025From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspectivecited by 22
  9. 2024HSIGene: A Foundation Model For Hyperspectral Image Generationcited by 21
  10. 2023ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentationcited by 20
  11. 2024Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurringcited by 20
  12. 2024LoFormer: Local Frequency Transformer for Image Deblurringcited by 19
  13. 2024Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restorationcited by 19
  14. 2024LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restorationcited by 18
  15. 2025BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splattingcited by 18
  16. 2023StableVQA: A Deep No-Reference Quality Assessment Model for Video Stabilitycited by 15
  17. 2024Phaseformer: Phase-based Attention Mechanism for Underwater Image Restoration and Beyondcited by 15
  18. 2023Mixed Hierarchy Network for Image Restorationcited by 14
  19. 2024Ultra-High-Definition Image Restoration: New Benchmarks and A Dual Interaction Prior-Driven Solutioncited by 14
  20. 2023On the unreasonable vulnerability of transformers for image restoration -- and an easy fixcited by 11
  21. 2025EAMamba: Efficient All-Around Vision State Space Model for Image Restorationcited by 10
  22. 2025One-Step Diffusion Model for Image Motion-Deblurringcited by 9
  23. 2024MixNet: Efficient Global Modeling for Ultra-High-Definition Image Restorationcited by 8
  24. 2024Domain-adaptive Video Deblurring via Test-time Blurringcited by 8
  25. 2024IPT-V2: Efficient Image Processing Transformer using Hierarchical Attentionscited by 7
  26. 2025DSwinIR: Rethinking Window-based Attention for Image Restorationcited by 7
  27. 2025EvoIR: Towards All-in-One Image Restoration via Evolutionary Frequency Modulationcited by 7
  28. 2026Neural Discrimination-Prompted Transformers for Efficient UHD Image Restoration and Enhancementcited by 7
  29. 2023Unfolding Once is Enough: A Deployment-Friendly Transformer Unit for Super-Resolutioncited by 6
  30. 2025MP-HSIR: A Multi-Prompt Framework for Universal Hyperspectral Image Restorationcited by 6
  31. 2025Deep Learning-Driven Ultra-High-Definition Image Restoration: A Surveycited by 6
  32. 2026Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restorationcited by 6
  33. 2023Deep Richardson-Lucy Deconvolution for Low-Light Image Deblurringcited by 5
  34. 2024Deep learning in motion deblurring: current status, benchmarks and future prospectscited by 5
  35. 2024Learning to Deblur Polarized Imagescited by 5
  36. 2024Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretizationcited by 5
  37. 2025BlurDM: A Blur Diffusion Model for Image Deblurringcited by 5
  38. 2022Meta Transferring for Deblurringcited by 4

50 most cited of 139 All 139 (JSON)