mlsanityData to 7 Oct 2026

You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction

arXiv 2205.14871 ↗First posted 30 May 2022cs.CVcited by 81

Not on the map. Why?

Abstract (arXiv)

Challenging illumination conditions (low-light, under-exposure and over-exposure) in the real world not only cast an unpleasant visual appearance but also taint the computer vision tasks. After camera captures the raw-RGB data, it renders standard sRGB images with image signal processor (ISP). By decomposing ISP pipeline into local and global image components, we propose a lightweight fast Illumination Adaptive Transformer (IAT) to restore the normal lit sRGB image from either low-light or under/over-exposure conditions. Specifically, IAT uses attention queries to represent and adjust the ISP-related parameters such as colour correction, gamma correction. With only ~90k parameters and ~0.004s processing speed, our IAT consistently achieves superior performance over SOTA on the current benchmark low-light enhancement and exposure correction datasets. Competitive experimental performance also demonstrates that our IAT significantly enhances object detection and semantic segmentation tasks under various light conditions. Training code and pretrained model is available at https://github.com/cuiziteng/Illumination-Adaptive-Transformer.

Key facts. Cited by 81 papers in the map (data through 7 Oct 2026). Builds on 47 of its 79 references that are in the map. First posted on arXiv 30 May 2022.

Builds on

47 of 79 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  8. 2020End-to-End Object Detection with Transformerscited by 7,384
  9. 2016Layer Normalizationcited by 5,579
  10. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  11. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  12. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
35 more
  1. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  2. 2018YOLOv3: An Incremental Improvementcited by 2,652
  3. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  4. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  5. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  6. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  7. 2020Pre-Trained Image Processing Transformercited by 891
  8. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  9. 2021Going deeper with Image Transformerscited by 759
  10. 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 720
  11. 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 541
  12. 2018Learning to See in the Darkcited by 459
  13. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modelingcited by 429
  14. 2019Kindling the Darkness: A Practical Low-light Image Enhancercited by 355
  15. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 338
  16. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  17. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  18. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  19. 2021TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditionscited by 243
  20. 2015LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancementcited by 224
  21. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  22. 2020Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-timecited by 163
  23. 2018Getting to Know Low-light Images with The Exclusively Dark Datasetcited by 157
  24. 2017DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networkscited by 156
  25. 2020A Physics-based Noise Formation Model for Extreme Low-light Raw Denoisingcited by 138
  26. 2020DeepLPF: Deep Local Parametric Filters for Image Enhancementcited by 107
  27. 2021Invertible Image Signal Processingcited by 94
  28. 2021Colorization Transformercited by 89
  29. 2021On the Connection between Local Attention and Dynamic Depth-wise Convolutioncited by 61
  30. 2022Multitask AET with Orthogonal Tangent Regularity for Dark Object Detectioncited by 59
  31. 2020Deep White-Balance Editingcited by 54
  32. 2018Distort-and-Recover: Color Enhancement using Deep Reinforcement Learningcited by 52
  33. 2021Auto White-Balance Correction for Mixed-Illuminant Scenescited by 22
  34. 2022Learning to Adapt to Lightcited by 21
  35. 2016Learning the image processing pipelinecited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 15; 2024: 18; 2025: 30; 2026: 14.

81 papers.

Sort:

By area:

  1. 2022UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormercited by 116
  2. 2023Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumptioncited by 35
  3. 2024GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrievalcited by 33
  4. 2025Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustmentcited by 27
  5. 2025DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolutioncited by 21
  6. 2024RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Imagescited by 19
  7. 2025I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactionscited by 17
  8. 2023PE-YOLO: Pyramid Enhancement Network for Dark Object Detectioncited by 12
  9. 2025MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devicescited by 12
  10. 2023Aleth-NeRF: Low-light Condition View Synthesis with Concealing Fieldscited by 9
  11. 20234K-Resolution Photo Exposure Correction at 125 FPS with ~8K Parameterscited by 9
  12. 2024You Only Look Around: Learning Illumination Invariant Feature for Low-light Object Detectioncited by 9
38 more
  1. 2024Wavelet-based Mamba with Fourier Adjustment for Low-light Image Enhancementcited by 8
  2. 2026Unifying Color and Lightness Correction with View-Adaptive Curve Adjustment for Robust 3D Novel View Synthesiscited by 8
  3. 2023Geometric-Aware Low-Light Image and Video Enhancement via Depth Guidancecited by 7
  4. 2024A Lightweight Low-Light Image Enhancement Network via Channel Prior and Gamma Correctioncited by 6
  5. 2023Self-Supervised Reversed Image Signal Processing via Reference-Guided Dynamic Parameter Selectioncited by 5
  6. 2023SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Devicecited by 5
  7. 2023Bootstrap Diffusion Model Curve Estimation for High Resolution Low-Light Image Enhancementcited by 5
  8. 2024MetaISP -- Exploiting Global Scene Structure for Accurate Multi-Device Color Renditioncited by 5
  9. 2025UltraFast-LiNET: Light-weight multi-scale shift convolutional network for real-time low-light image enhancementcited by 5
  10. 2023Low-Light Image Enhancement by Learning Contrastive Representations in Spatial and Frequency Domainscited by 4
  11. 2023FLIGHT Mode On: A Feather-Light Network for Low-Light Image Enhancementcited by 4
  12. 2023Learning a Single Convolutional Layer Model for Low Light Image Enhancementcited by 4
  13. 2025Discovering an Image-Adaptive Coordinate System for Photography Processingcited by 4
  14. 2025Structure-guided Diffusion Transformer for Low-Light Image Enhancementcited by 4
  15. 2025CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid Predictioncited by 4
  16. 2024Text in the Dark: Extremely Low-Light Text Image Enhancementcited by 3
  17. 2024Unified-EGformer: Exposure Guided Lightweight Transformer for Mixed-Exposure Image Enhancementcited by 3
  18. 2024Rethinking Theoretical Illumination for Efficient Low-Light Image Enhancementcited by 3
  19. 2024OSMamba: Omnidirectional Spectral Mamba with Dual-Domain Prior Generator for Exposure Correctioncited by 3
  20. 2025Illuminating Darkness: Learning to Enhance Low-light Images In-the-Wildcited by 3
  21. 2025YOLO-LLTS: Real-Time Low-Light Traffic Sign Detection via Prior-Guided Enhancement and Multibranch Feature Interactioncited by 3
  22. 2025Robust Low-light Scene Restoration via Illumination Transitioncited by 3
  23. 2025From Enhancement to Understanding: Build a Generalized Bridge for Low-light Vision via Semantically Consistent Unsupervised Fine-tuningcited by 3
  24. 2023Simplifying Low-Light Image Enhancement Networks with Relative Loss Functionscited by 2
  25. 2024DiffLoss: unleashing diffusion model as constraint for training image restoration networkcited by 2
  26. 2024From Darkness to Detail: Frequency-Aware SSMs for Low-Light Visioncited by 2
  27. 2024Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancementcited by 2
  28. 2025RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images and A Benchmarkcited by 2
  29. 2025DRWKV: Focusing on Object Edges for Low-Light Image Enhancementcited by 2
  30. 2026Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinexcited by 2
  31. 2022Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformercited by 1
  32. 2022ExReg: Wide-range Photo Exposure Correction via a Multi-dimensional Regressor with Attentioncited by 1
  33. 2025LENVIZ: A High-Resolution Low-Exposure Night Vision Benchmark Datasetcited by 1
  34. 2025Towards Realistic Low-Light Image Enhancement via ISP Driven Data Modelingcited by 1
  35. 2025ModalFormer: Multimodal Transformer for Low-Light Image Enhancementcited by 1
  36. 2025Coupled Degradation Modeling and Fusion: A VLM-Guided Degradation-Coupled Network for Degradation-Aware Infrared and Visible Image Fusioncited by 1
  37. 2025Beyond Darkness: Thermal-Supervised 3D Gaussian Splatting for Low-Light Novel View Synthesiscited by 1
  38. 2022A Survey on Causal Representation Learning and Future Work for Medical Image Analysiscited by 0

50 most cited of 81 All 81 (JSON)