# Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images

arXiv: https://arxiv.org/abs/2504.09621 · HTML: https://mlsanity.com/paper/2504.09621/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 63 references that are in the map.
- First posted on arXiv 13 Apr 2025.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [FFA-Net: Feature Fusion Attention Network for Single Image Dehazing](https://mlsanity.com/paper/1911.07559/) (2019)
- [Vision Transformers for Single Image Dehazing](https://mlsanity.com/paper/2204.03883/) (2022)
- [Multi-Scale Boosted Dehazing Network with Dense Feature Fusion](https://mlsanity.com/paper/2004.13388/) (2020)
- [From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation](https://mlsanity.com/paper/2206.03208/) (2022)
- [Interpreting Super-Resolution Networks with Local Attribution Maps](https://mlsanity.com/paper/2011.11036/) (2020)
- [O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images](https://mlsanity.com/paper/1804.05101/) (2018)
- [DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention](https://mlsanity.com/paper/2301.04805/) (2023)
- [HyperAttention: Long-context Attention in Near-Linear Time](https://mlsanity.com/paper/2310.05869/) (2023)
- [Curricular Contrastive Regularization for Physics-aware Single Image Dehazing](https://mlsanity.com/paper/2303.14218/) (2023)
- [MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing](https://mlsanity.com/paper/2308.14036/) (2023)
- [Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis](https://mlsanity.com/paper/2202.07728/) (2022)
- [Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing](https://mlsanity.com/paper/2403.01105/) (2024)
- [Evaluating Feature Attribution Methods in the Image Domain](https://mlsanity.com/paper/2202.12270/) (2022)
- [MixDehazeNet : Mix Structure Block For Image Dehazing Network](https://mlsanity.com/paper/2305.17654/) (2023)
- [IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradients](https://mlsanity.com/paper/2303.14242/) (2023)
- [xT: Nested Tokenization for Larger Context in Large Images](https://mlsanity.com/paper/2403.01915/) (2024)
- [Haze-Aware Attention Network for Single-Image Dehazing](https://mlsanity.com/paper/2407.11505/) (2024)

## Built on by (most cited first, 7 of 7)

- [LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing](https://mlsanity.com/paper/2605.11508/) (2026)
- [UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache](https://mlsanity.com/paper/2505.14010/) (2025)
- [UHDRes: Ultra-High-Definition Image Restoration via Dual-Domain Decoupled Spectral Modulation](https://mlsanity.com/paper/2511.05009/) (2025)
- [On the Global Photometric Alignment for Low-Level Vision](https://mlsanity.com/paper/2604.08172/) (2026)
- [Physically-Guided Optical Inversion Enable Non-Contact Side-Channel Attack on Isolated Screens](https://mlsanity.com/paper/2604.13419/) (2026)
- [From Fog Chamber to Aircraft Window: Pixel-Registered Imaging and Synthetic Fine-Tuning Enable Cross-Domain Defogging](https://mlsanity.com/paper/2606.29093/) (2026)
- [RTE-FM-Dehazer: Radiative Transfer Equation Inspired Flow Matching for Real-World Image Dehazing](https://mlsanity.com/paper/2607.01748/) (2026)

## Abstract (arXiv)

Global contextual information and local detail features are essential for haze removal tasks. Deep learning models perform well on small, low-resolution images, but they encounter difficulties with large, high-resolution ones due to GPU memory limitations. As a compromise, they often resort to image slicing or downsampling. The former diminishes global information, while the latter discards high-frequency details. To address these challenges, we propose DehazeXL, a haze removal method that effectively balances global context and local feature extraction, enabling end-to-end modeling of large images on mainstream GPU hardware. Additionally, to evaluate the efficiency of global context utilization in haze removal performance, we design a visual attribution method tailored to the characteristics of haze removal tasks. Finally, recognizing the lack of benchmark datasets for haze removal in large images, we have developed an ultra-high-resolution haze removal dataset (8KDehaze) to support model training and testing. It includes 10000 pairs of clear and hazy remote sensing images, each sized at 8192 × 8192 pixels. Extensive experiments demonstrate that DehazeXL can infer images up to 10240 × 10240 pixels with only 21 GB of memory, achieving state-of-the-art results among all evaluated methods. The source code and experimental dataset are available at https://github.com/CastleChen339/DehazeXL.