mlsanityData to 7 Oct 2026

I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images

arXiv 1804.05091 ↗First posted 13 Apr 2018cs.CVcited by 64

Not on the map. Why?

Abstract (arXiv)

Image dehazing has become an important computational imaging topic in the recent years. However, due to the lack of ground truth images, the comparison of dehazing methods is not straightforward, nor objective. To overcome this issue we introduce a new dataset -named I-HAZE- that contains 35 image pairs of hazy and corresponding haze-free (ground-truth) indoor images. Different from most of the existing dehazing databases, hazy images have been generated using real haze produced by a professional haze machine. For easy color calibration and improved assessment of dehazing algorithms, each scene include a MacBeth color checker. Moreover, since the images are captured in a controlled environment, both haze-free and hazy images are captured under the same illumination conditions. This represents an important advantage of the I-HAZE dataset that allows us to objectively compare the existing image dehazing techniques using traditional image quality metrics such as PSNR and SSIM.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 9; 2023: 8; 2024: 13; 2025: 18; 2026: 10.

64 papers.

Sort:

By area:

  1. 2022Vision Transformers for Single Image Dehazingcited by 255
  2. 2022Not Just Streaks: Towards Ground Truth for Single Image Derainingcited by 31
  3. 2021A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learningcited by 19
  4. 2025Multi-Agent Image Restorationcited by 19
  5. 2022Source-Free Domain Adaptation for Real-world Image Dehazingcited by 17
  6. 2023Frequency Compensated Diffusion Model for Real-scene Dehazingcited by 17
  7. 2022Single UHD Image Dehazing via Interpretable Pyramid Networkcited by 13
  8. 2023Let Segment Anything Help Image Dehazecited by 13
  9. 2024GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restorationcited by 13
  10. 2023Prompt-based test-time real image dehazing: a novel pipelinecited by 12
  11. 2025Frequency Domain-Based Diffusion Model for Unpaired Image Dehazingcited by 11
  12. 2022A Multi-purpose Realistic Haze Benchmark with Quantifiable Haze Levels and Ground Truthcited by 9
38 more
  1. 2025When Schr"odinger Bridge Meets Real-World Image Dehazing with Unpaired Trainingcited by 8
  2. 2021Rank-One Prior: Toward Real-Time Scene Recoverycited by 7
  3. 2025PHATNet: A Physics-guided Haze Transfer Network for Domain-adaptive Real-world Image Dehazingcited by 6
  4. 2025Generative AI in Depth: A Survey of Recent Advances, Model Variants, and Real-World Applicationscited by 5
  5. 2025UniSER: A Foundation Model for Unified Soft Effects Removalcited by 5
  6. 2021ZeroScatter: Domain Transfer for Long Distance Imaging and Vision through Scattering Mediacited by 4
  7. 2022Mutual Learning for Domain Adaptation: Self-distillation Image Dehazing Network with Sample-cyclecited by 4
  8. 2022Robust Single Image Dehazing Based on Consistent and Contrast-Assisted Reconstructioncited by 4
  9. 2023Reliable Image Dehazing by NeRFcited by 4
  10. 2023SUD2: Supervision by Denoising Diffusion Models for Image Reconstructioncited by 4
  11. 2024WaveletFormerNet: A Transformer-based Wavelet Network for Real-world Non-homogeneous and Dense Fog Removalcited by 4
  12. 2024HazeSpace2M: A Dataset for Haze Aware Single Image Dehazingcited by 4
  13. 2024NeuroPump: Simultaneous Geometric and Color Rectification for Underwater Imagescited by 4
  14. 2025FDG-Diff: Frequency-Domain-Guided Diffusion Framework for Compressed Hazy Image Restorationcited by 4
  15. 2025HazeFlow: Revisit Haze Physical Model as ODE and Non-Homogeneous Haze Generation for Real-World Dehazingcited by 4
  16. 2023Fooling the Image Dehazing Models by First Order Gradientcited by 3
  17. 2023RB-Dust -- A Reference-based Dataset for Vision-based Dust Removalcited by 3
  18. 2024WaveDH: Wavelet Sub-bands Guided ConvNet for Efficient Image Dehazingcited by 3
  19. 2024Distilled Pooling Transformer Encoder for Efficient Realistic Image Dehazingcited by 3
  20. 2025UR2P-Dehaze: Learning a Simple Image Dehaze Enhancer via Unpaired Rich Physical Priorcited by 3
  21. 2026Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Executioncited by 3
  22. 2021Unsupervised Neural Rendering for Image Hazingcited by 2
  23. 2022Compound Multi-branch Feature Fusion for Real Image Restorationcited by 2
  24. 2022Deep Semantic Statistics Matching (D2SM) Denoising Networkcited by 2
  25. 2024LMHaze: Intensity-aware Image Dehazing with a Large-scale Multi-intensity Real Haze Datasetcited by 2
  26. 2025DGIQA: Depth-guided Feature Attention and Refinement for Generalizable Image Quality Assessmentcited by 2
  27. 2023Latent Graph Attention for Enhanced Spatial Contextcited by 1
  28. 2024PANet: A Physics-guided Parametric Augmentation Net for Image Dehazing by Hazingcited by 1
  29. 2024Single Image Dehazing Using Scene Depth Orderingcited by 1
  30. 2024DRACO-DehazeNet: An Efficient Image Dehazing Network Combining Detail Recovery and a Novel Contrastive Learning Paradigmcited by 1
  31. 2025ProDehaze: Prompting Diffusion Models Toward Faithful Image Dehazingcited by 1
  32. 2025UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cachecited by 1
  33. 2025HiRQA: Hierarchical Ranking and Quality Alignment for Opinion-Unaware Image Quality Assessmentcited by 1
  34. 2025RPD-Diff: Region-Adaptive Physics-Guided Diffusion Model for Visibility Enhancement under Dense and Non-Uniform Hazecited by 1
  35. 2025Clear Roads, Clear Vision: Advancements in Multi-Weather Restoration for Smart Transportationcited by 1
  36. 2026LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazingcited by 1
  37. 2021Efficient Re-parameterization Residual Attention Network For Nonhomogeneous Image Dehazingcited by 0
  38. 20213D modelling of survey scene from images enhanced with a multi-exposure fusioncited by 0

50 most cited of 64 All 64 (JSON)