mlsanityData to 7 Oct 2026

O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images

arXiv 1804.05101 ↗First posted 13 Apr 2018cs.CVcited by 95

Not on the map. Why?

Abstract (arXiv)

Haze removal or dehazing is a challenging ill-posed problem that has drawn a significant attention in the last few years. Despite this growing interest, the scientific community is still lacking a reference dataset to evaluate objectively and quantitatively the performance of proposed dehazing methods. The few datasets that are currently considered, both for assessment and training of learning-based dehazing techniques, exclusively rely on synthetic hazy images. To address this limitation, we introduce the first outdoor scenes database (named O-HAZE) composed of pairs of real hazy and corresponding haze-free images. In practice, hazy images have been captured in presence of real haze, generated by professional haze machines, and OHAZE contains 45 different outdoor scenes depicting the same visual content recorded in haze-free and hazy conditions, under the same illumination parameters. To illustrate its usefulness, O-HAZE is used to compare a representative set of state-of-the-art dehazing techniques, using traditional image quality metrics such as PSNR, SSIM and CIEDE2000. This reveals the limitations of current techniques, and questions some of their underlying assumptions.

Key facts. Cited by 95 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: 14; 2022: 15; 2023: 11; 2024: 20; 2025: 19; 2026: 16.

95 papers.

Sort:

By area:

  1. 2022Vision Transformers for Single Image Dehazingcited by 255
  2. 2023MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazingcited by 81
  3. 2024Diffusion Models in Low-Level Vision: A Surveycited by 73
  4. 2024PromptFix: You Prompt and We Fix the Photocited by 40
  5. 2022Not Just Streaks: Towards Ground Truth for Single Image Derainingcited by 31
  6. 2022Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removalcited by 28
  7. 2023ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Renderingcited by 28
  8. 2024Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restorationcited by 21
  9. 2021A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learningcited by 19
  10. 2023Frequency Compensated Diffusion Model for Real-scene Dehazingcited by 17
  11. 2021A Two-branch Neural Network for Non-homogeneous Dehazing via Ensemble Learningcited by 16
  12. 2021GridDehazeNet+: An Enhanced Multi-Scale Network with Intra-Task Knowledge Transfer for Single Image Dehazingcited by 14
38 more
  1. 2026Learning Continuous Wasserstein Barycenter Space for Generalized All-in-One Image Restorationcited by 14
  2. 2022Single UHD Image Dehazing via Interpretable Pyramid Networkcited by 13
  3. 2023Let Segment Anything Help Image Dehazecited by 13
  4. 2024Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restorationcited by 13
  5. 2024GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restorationcited by 13
  6. 2023Prompt-based test-time real image dehazing: a novel pipelinecited by 12
  7. 2025Prior-guided Hierarchical Harmonization Network for Efficient Image Dehazingcited by 12
  8. 2025Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Trainingcited by 12
  9. 2025Frequency Domain-Based Diffusion Model for Unpaired Image Dehazingcited by 11
  10. 2022A Multi-purpose Realistic Haze Benchmark with Quantifiable Haze Levels and Ground Truthcited by 9
  11. 2023A Data-Centric Solution to NonHomogeneous Dehazing via Vision Transformercited by 9
  12. 2024SynFog: A Photo-realistic Synthetic Fog Dataset based on End-to-end Imaging Simulation for Advancing Real-World Defogging in Autonomous Drivingcited by 9
  13. 2024Towards Image Ambient Lighting Normalizationcited by 9
  14. 2021Complementary Feature Enhanced Network with Vision Transformer for Image Dehazingcited by 8
  15. 2025When Schr"odinger Bridge Meets Real-World Image Dehazing with Unpaired Trainingcited by 8
  16. 2026CLIP-Guided Data Augmentation for Night-Time Image Dehazingcited by 8
  17. 2021Rank-One Prior: Toward Real-Time Scene Recoverycited by 7
  18. 2025Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Imagescited by 7
  19. 2021Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoningcited by 6
  20. 2025PHATNet: A Physics-guided Haze Transfer Network for Domain-adaptive Real-world Image Dehazingcited by 6
  21. 2026From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmarkcited by 6
  22. 2024Stability and Generalizability in SDE Diffusion Models with Measure-Preserving Dynamicscited by 5
  23. 2025UniSER: A Foundation Model for Unified Soft Effects Removalcited by 5
  24. 2026Bilevel Layer-Positioning LoRA for Real Image Dehazingcited by 5
  25. 2021ZeroScatter: Domain Transfer for Long Distance Imaging and Vision through Scattering Mediacited by 4
  26. 2022Robust Single Image Dehazing Based on Consistent and Contrast-Assisted Reconstructioncited by 4
  27. 2023Reliable Image Dehazing by NeRFcited by 4
  28. 2023SUD2: Supervision by Denoising Diffusion Models for Image Reconstructioncited by 4
  29. 2024WaveletFormerNet: A Transformer-based Wavelet Network for Real-world Non-homogeneous and Dense Fog Removalcited by 4
  30. 2024Emphasizing Crucial Features for Efficient Image Restorationcited by 4
  31. 2024HazeSpace2M: A Dataset for Haze Aware Single Image Dehazingcited by 4
  32. 2025FDG-Diff: Frequency-Domain-Guided Diffusion Framework for Compressed Hazy Image Restorationcited by 4
  33. 2025HazeFlow: Revisit Haze Physical Model as ODE and Non-Homogeneous Haze Generation for Real-World Dehazingcited by 4
  34. 2021FWB-Net:Front White Balance Network for Color Shift Correction in Single Image Dehazing via Atmospheric Light Estimationcited by 3
  35. 2022A comprehensive benchmark analysis for sand dust image reconstructioncited by 3
  36. 2023Fooling the Image Dehazing Models by First Order Gradientcited by 3
  37. 2023RB-Dust -- A Reference-based Dataset for Vision-based Dust Removalcited by 3
  38. 2024Distilled Pooling Transformer Encoder for Efficient Realistic Image Dehazingcited by 3

50 most cited of 95 All 95 (JSON)