mlsanityData to 7 Oct 2026

MAXIM: Multi-Axis MLP for Image Processing

arXiv 2201.02973 ↗First posted 9 Jan 2022eess.IV cs.CVcited by 301

Not on the map. Why?

Cited by 27 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent progress on Transformers and multi-layer perceptron (MLP) models provide new network architectural designs for computer vision tasks. Although these models proved to be effective in many vision tasks such as image recognition, there remain challenges in adapting them for low-level vision. The inflexibility to support high-resolution images and limitations of local attention are perhaps the main bottlenecks. In this work, we present a multi-axis MLP based architecture called MAXIM, that can serve as an efficient and flexible general-purpose vision backbone for image processing tasks. MAXIM uses a UNet-shaped hierarchical structure and supports long-range interactions enabled by spatially-gated MLPs. Specifically, MAXIM contains two MLP-based building blocks: a multi-axis gated MLP that allows for efficient and scalable spatial mixing of local and global visual cues, and a cross-gating block, an alternative to cross-attention, which accounts for cross-feature conditioning. Both these modules are exclusively based on MLPs, but also benefit from being both global and `fully-convolutional', two properties that are desirable for image processing. Our extensive experimental results show that the proposed MAXIM model achieves state-of-the-art performance on more than ten benchmarks across a range of image processing tasks, including denoising, deblurring, deraining, dehazing, and enhancement while requiring fewer or comparable numbers of parameters and FLOPs than competitive models. The source code and trained models will be available at urlhttps://github.com/google-research/maxim.

Key facts. Cited by 301 papers in the map (data through 7 Oct 2026). Builds on 96 of its 123 references that are in the map. First posted on arXiv 9 Jan 2022.

Builds on

96 of 123 references.

References · 96

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2016Layer Normalizationcited by 5,579
  8. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  9. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  10. 2017Squeeze-and-Excitation Networkscited by 4,763
  11. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  12. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
38 more
  1. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  2. 2017Non-local Neural Networkscited by 2,290
  3. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  4. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  5. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  6. 2021ViViT: A Video Vision Transformercited by 1,610
  7. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  8. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  9. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  10. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  11. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  12. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  13. 2020Pre-Trained Image Processing Transformercited by 891
  14. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  15. 2021Multi-Stage Progressive Image Restorationcited by 813
  16. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  17. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  18. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  19. 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 720
  20. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  21. 2019EnlightenGAN: Deep Light Enhancement without Paired Supervisioncited by 466
  22. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  23. 2017Benchmarking Single Image Dehazing and Beyondcited by 445
  24. 2019MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentationcited by 370
  25. 2020TransTrack: Multiple Object Tracking with Transformercited by 370
  26. 2021Pay Attention to MLPscited by 367
  27. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 366
  28. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 361
  29. 2019Kindling the Darkness: A Practical Low-light Image Enhancercited by 355
  30. 2016Deep Joint Rain Detection and Removal from a Single Imagecited by 351
  31. 2021FNet: Mixing Tokens with Fourier Transformscited by 343
  32. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  33. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 338
  34. 2018Scale-recurrent Network for Deep Image Deblurringcited by 332
  35. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 324
  36. 2016DehazeNet: An End-to-End System for Single Image Haze Removalcited by 313
  37. 2019FFA-Net: Feature Fusion Attention Network for Single Image Dehazingcited by 307
  38. 2018Toward Convolutional Blind Denoising of Real Photographscited by 274

50 most cited of 96 All 96 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 36; 2023: 85; 2024: 85; 2025: 64; 2026: 31.

301 papers.

Sort:

By area:

  1. 2022Simple Baselines for Image Restorationcited by 701
  2. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  3. 2022Activating More Pixels in Image Super-Resolution Transformercited by 433
  4. 2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
  5. 2022CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformerscited by 227
  6. 2022Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Modelscited by 215
  7. 2023Image Restoration with Mean-Reverting Stochastic Differential Equationscited by 182
  8. 2024A Survey on Diffusion Models for Inverse Problemscited by 173
  9. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 168
  10. 2022Efficient Frequency Domain-based Transformers for High-Quality Image Deblurringcited by 164
  11. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 164
  12. 2023Efficient and Explicit Modelling of Image Hierarchies for Image Restorationcited by 145
38 more
  1. 2024InstructIR: High-Quality Image Restoration Following Human Instructionscited by 139
  2. 2023Dual Aggregation Transformer for Image Super-Resolutioncited by 124
  3. 2023PromptIR: Prompting for All-in-One Blind Image Restorationcited by 113
  4. 2023Controlling Vision-Language Models for Multi-Task Image Restorationcited by 108
  5. 2024AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulationcited by 108
  6. 2022HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutionscited by 103
  7. 2023Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Modelscited by 86
  8. 2022Accurate Image Restoration with Attention Retractable Transformercited by 85
  9. 2023Curricular Contrastive Regularization for Physics-aware Single Image Dehazingcited by 83
  10. 2022You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correctioncited by 81
  11. 2023MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazingcited by 81
  12. 2022Fast Vision Transformers with HiLo Attentioncited by 78
  13. 2023ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restorationcited by 77
  14. 2022Multiscale Structure Guided Diffusion for Image Deblurringcited by 76
  15. 2024Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Modelcited by 73
  16. 2024Restoring Images in Adverse Weather Conditions via Histogram Transformercited by 73
  17. 2023HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative perception with vision transformercited by 70
  18. 2023Residual Denoising Diffusion Modelscited by 68
  19. 2023HAT: Hybrid Attention Transformer for Image Restorationcited by 64
  20. 2023GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditionscited by 62
  21. 2022Bridging the Domain Gap for Multi-Agent Perceptioncited by 60
  22. 2023Zero-Shot Noise2Noise: Efficient Image Denoising without any Datacited by 59
  23. 2023GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restorationcited by 58
  24. 2023Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancementcited by 57
  25. 2024The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Reportcited by 57
  26. 2023A Comparative Study of Image Restoration Networks for General Backbone Network Designcited by 56
  27. 2024Bidirectional Multi-Scale Implicit Neural Representations for Image Derainingcited by 54
  28. 2022Signal Processing for Implicit Neural Representationscited by 46
  29. 2024SkateFormer: Skeletal-Temporal Transformer for Human Action Recognitioncited by 46
  30. 2023Prompt-In-Prompt Learning for Universal Image Restorationcited by 43
  31. 2022Domain Adaptive Object Detection for Autonomous Driving under Foggy Weathercited by 41
  32. 2023Image Restoration Through Generalized Ornstein-Uhlenbeck Bridgecited by 41
  33. 2024An Intelligent Agentic System for Complex Image Restoration Problemscited by 41
  34. 2023Single Image Reflection Separation via Component Synergycited by 38
  35. 2024Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Datasetcited by 38
  36. 2023Xformer: Hybrid X-Shaped Transformer for Image Denoisingcited by 37
  37. 2024Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registrationcited by 37
  38. 2023How Much Temporal Long-Term Context is Needed for Action Segmentation?cited by 36

50 most cited of 301 All 301 (JSON)