# LMHaze: Intensity-aware Image Dehazing with a Large-scale Multi-intensity Real Haze Dataset

arXiv: https://arxiv.org/abs/2410.16095 · HTML: https://mlsanity.com/paper/2410.16095/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Mamba for image restoration, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 29 of its 61 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Placed in

- State-space sequence models (S4, Mamba) / [Mamba for image restoration](https://mlsanity.com/ssm/mamba-for-image-restoration/)

## Builds on (most cited first, 29 of 29)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration](https://mlsanity.com/paper/2311.04257/) (2023)
- [Hungry Hungry Hippos: Towards Language Modeling with State Space Models](https://mlsanity.com/paper/2212.14052/) (2022)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [DehazeNet: An End-to-End System for Single Image Haze Removal](https://mlsanity.com/paper/1601.07661/) (2016)
- [FFA-Net: Feature Fusion Attention Network for Single Image Dehazing](https://mlsanity.com/paper/1911.07559/) (2019)
- [Long Range Language Modeling via Gated State Spaces](https://mlsanity.com/paper/2206.13947/) (2022)
- [GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing](https://mlsanity.com/paper/1908.03245/) (2019)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)
- [NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images](https://mlsanity.com/paper/2005.03560/) (2020)
- [Domain Adaptation for Image Dehazing](https://mlsanity.com/paper/2005.04668/) (2020)
- [Dense Haze: A benchmark for image dehazing with dense-haze and haze-free images](https://mlsanity.com/paper/1904.02904/) (2019)
- [O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images](https://mlsanity.com/paper/1804.05101/) (2018)
- [MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing](https://mlsanity.com/paper/2308.14036/) (2023)
- [FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazing](https://mlsanity.com/paper/2001.06968/) (2020)
- [From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data](https://mlsanity.com/paper/2108.02934/) (2021)
- [I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images](https://mlsanity.com/paper/1804.05091/) (2018)
- [Language-driven All-in-one Adverse Weather Removal](https://mlsanity.com/paper/2312.01381/) (2023)
- [UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning](https://mlsanity.com/paper/2205.01871/) (2022)
- [FIFO: Learning Fog-invariant Features for Foggy Scene Segmentation](https://mlsanity.com/paper/2204.01587/) (2022)
- [End-to-End United Video Dehazing and Detection](https://mlsanity.com/paper/1709.03919/) (2017)
- [Joint Stereo Video Deblurring, Scene Flow Estimation and Moving Object Segmentation](https://mlsanity.com/paper/1910.02442/) (2019)
- [BotBuster: Multi-platform Bot Detection Using A Mixture of Experts](https://mlsanity.com/paper/2207.13658/) (2022)
- [LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network](https://mlsanity.com/paper/2307.09815/) (2023)

## Built on by (most cited first, 2 of 2)

- [UniSER: A Foundation Model for Unified Soft Effects Removal](https://mlsanity.com/paper/2511.14183/) (2025)
- [Backbone-Agnostic Stochastic Perturbation Learning for End-to-End Real-World Image Dehazing](https://mlsanity.com/paper/2607.11623/) (2026)

## Abstract (arXiv)

Image dehazing has drawn a significant attention in recent years. Learning-based methods usually require paired hazy and corresponding ground truth (haze-free) images for training. However, it is difficult to collect real-world image pairs, which prevents developments of existing methods. Although several works partially alleviate this issue by using synthetic datasets or small-scale real datasets. The haze intensity distribution bias and scene homogeneity in existing datasets limit the generalization ability of these methods, particularly when encountering images with previously unseen haze intensities. In this work, we present LMHaze, a large-scale, high-quality real-world dataset. LMHaze comprises paired hazy and haze-free images captured in diverse indoor and outdoor environments, spanning multiple scenarios and haze intensities. It contains over 5K high-resolution image pairs, surpassing the size of the biggest existing real-world dehazing dataset by over 25 times. Meanwhile, to better handle images with different haze intensities, we propose a mixture-of-experts model based on Mamba (MoE-Mamba) for dehazing, which dynamically adjusts the model parameters according to the haze intensity. Moreover, with our proposed dataset, we conduct a new large multimodal model (LMM)-based benchmark study to simulate human perception for evaluating dehazed images. Experiments demonstrate that LMHaze dataset improves the dehazing performance in real scenarios and our dehazing method provides better results compared to state-of-the-art methods.