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

arXiv: https://arxiv.org/abs/1804.05091 · HTML: https://mlsanity.com/paper/1804.05091/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2018.

## Built on by (most cited first, 30 of 64)

- [Vision Transformers for Single Image Dehazing](https://mlsanity.com/paper/2204.03883/) (2022)
- [Not Just Streaks: Towards Ground Truth for Single Image Deraining](https://mlsanity.com/paper/2206.10779/) (2022)
- [Multi-Agent Image Restoration](https://mlsanity.com/paper/2503.09403/) (2025)
- [A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning](https://mlsanity.com/paper/2106.03323/) (2021)
- [Source-Free Domain Adaptation for Real-world Image Dehazing](https://mlsanity.com/paper/2207.06644/) (2022)
- [Frequency Compensated Diffusion Model for Real-scene Dehazing](https://mlsanity.com/paper/2308.10510/) (2023)
- [Single UHD Image Dehazing via Interpretable Pyramid Network](https://mlsanity.com/paper/2202.08589/) (2022)
- [Let Segment Anything Help Image Dehaze](https://mlsanity.com/paper/2306.15870/) (2023)
- [GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration](https://mlsanity.com/paper/2411.17687/) (2024)
- [Prompt-based test-time real image dehazing: a novel pipeline](https://mlsanity.com/paper/2309.17389/) (2023)
- [Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing](https://mlsanity.com/paper/2507.01275/) (2025)
- [A Multi-purpose Realistic Haze Benchmark with Quantifiable Haze Levels and Ground Truth](https://mlsanity.com/paper/2206.06427/) (2022)
- [When Schr"odinger Bridge Meets Real-World Image Dehazing with Unpaired Training](https://mlsanity.com/paper/2507.09524/) (2025)
- [Rank-One Prior: Toward Real-Time Scene Recovery](https://mlsanity.com/paper/2103.17126/) (2021)
- [PHATNet: A Physics-guided Haze Transfer Network for Domain-adaptive Real-world Image Dehazing](https://mlsanity.com/paper/2507.14826/) (2025)
- [Generative AI in Depth: A Survey of Recent Advances, Model Variants, and Real-World Applications](https://mlsanity.com/paper/2510.21887/) (2025)
- [UniSER: A Foundation Model for Unified Soft Effects Removal](https://mlsanity.com/paper/2511.14183/) (2025)
- [ZeroScatter: Domain Transfer for Long Distance Imaging and Vision through Scattering Media](https://mlsanity.com/paper/2102.05847/) (2021)
- [Mutual Learning for Domain Adaptation: Self-distillation Image Dehazing Network with Sample-cycle](https://mlsanity.com/paper/2203.09430/) (2022)
- [Robust Single Image Dehazing Based on Consistent and Contrast-Assisted Reconstruction](https://mlsanity.com/paper/2203.15325/) (2022)
- [Reliable Image Dehazing by NeRF](https://mlsanity.com/paper/2303.09153/) (2023)
- [SUD2: Supervision by Denoising Diffusion Models for Image Reconstruction](https://mlsanity.com/paper/2303.09642/) (2023)
- [WaveletFormerNet: A Transformer-based Wavelet Network for Real-world Non-homogeneous and Dense Fog Removal](https://mlsanity.com/paper/2401.04550/) (2024)
- [HazeSpace2M: A Dataset for Haze Aware Single Image Dehazing](https://mlsanity.com/paper/2409.17432/) (2024)
- [NeuroPump: Simultaneous Geometric and Color Rectification for Underwater Images](https://mlsanity.com/paper/2412.15890/) (2024)
- [FDG-Diff: Frequency-Domain-Guided Diffusion Framework for Compressed Hazy Image Restoration](https://mlsanity.com/paper/2501.12832/) (2025)
- [HazeFlow: Revisit Haze Physical Model as ODE and Non-Homogeneous Haze Generation for Real-World Dehazing](https://mlsanity.com/paper/2509.18190/) (2025)
- [Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution](https://mlsanity.com/paper/2606.28971/) (2026)
- [Fooling the Image Dehazing Models by First Order Gradient](https://mlsanity.com/paper/2303.17255/) (2023)
- [RB-Dust -- A Reference-based Dataset for Vision-based Dust Removal](https://mlsanity.com/paper/2306.07244/) (2023)

## 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.