# Single UHD Image Dehazing via Interpretable Pyramid Network

arXiv: https://arxiv.org/abs/2202.08589 · HTML: https://mlsanity.com/paper/2202.08589/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 45 references that are in the map.
- First posted on arXiv 17 Feb 2022.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (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)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)
- [Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding](https://mlsanity.com/paper/2103.15358/) (2021)
- [HRFormer: High-Resolution Transformer for Dense Prediction](https://mlsanity.com/paper/2110.09408/) (2021)
- [Domain Adaptation for Image Dehazing](https://mlsanity.com/paper/2005.04668/) (2020)
- [O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images](https://mlsanity.com/paper/1804.05101/) (2018)
- [Gated Context Aggregation Network for Image Dehazing and Deraining](https://mlsanity.com/paper/1811.08747/) (2018)
- [DeepISP: Towards Learning an End-to-End Image Processing Pipeline](https://mlsanity.com/paper/1801.06724/) (2018)
- [FaPN: Feature-aligned Pyramid Network for Dense Image Prediction](https://mlsanity.com/paper/2108.07058/) (2021)
- [Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables](https://mlsanity.com/paper/2108.08697/) (2021)
- [I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images](https://mlsanity.com/paper/1804.05091/) (2018)
- [High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network](https://mlsanity.com/paper/2105.09188/) (2021)
- [Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification](https://mlsanity.com/paper/1904.04975/) (2019)
- [Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer](https://mlsanity.com/paper/2104.05376/) (2021)
- [StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement](https://mlsanity.com/paper/2107.12898/) (2021)
- [An All-in-One Network for Dehazing and Beyond](https://mlsanity.com/paper/1707.06543/) (2017)
- [Progressive Feature Fusion Network for Realistic Image Dehazing](https://mlsanity.com/paper/1810.02283/) (2018)
- [BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policies](https://mlsanity.com/paper/2108.09376/) (2021)
- [Unfolding Taylor's Approximations for Image Restoration](https://mlsanity.com/paper/2109.03442/) (2021)

## Built on by (most cited first, 13 of 13)

- [Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution](https://mlsanity.com/paper/2308.01738/) (2023)
- [Textual Prompt Guided Image Restoration](https://mlsanity.com/paper/2312.06162/) (2023)
- [Self-Supervised Video Desmoking for Laparoscopic Surgery](https://mlsanity.com/paper/2403.11192/) (2024)
- [Real-World Remote Sensing Image Dehazing: Benchmark and Baseline](https://mlsanity.com/paper/2503.17966/) (2025)
- [A Multi-purpose Realistic Haze Benchmark with Quantifiable Haze Levels and Ground Truth](https://mlsanity.com/paper/2206.06427/) (2022)
- [Deep Learning-Driven Ultra-High-Definition Image Restoration: A Survey](https://mlsanity.com/paper/2505.16161/) (2025)
- [Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement](https://mlsanity.com/paper/2510.07961/) (2025)
- [Encoder-minimal and Decoder-minimal Framework for Remote Sensing Image Dehazing](https://mlsanity.com/paper/2312.07849/) (2023)
- [Cross Paradigm Representation and Alignment Transformer for Image Deraining](https://mlsanity.com/paper/2504.16455/) (2025)
- [Advancements and Trends in Ultra-High-Resolution Image Processing: An Overview](https://mlsanity.com/paper/2312.00250/) (2023)
- [Multi-Exposure Image Fusion via Distilled 3D LUT Grid with Editable Mode](https://mlsanity.com/paper/2412.13749/) (2024)
- [Efficient Real-World Dehazing via Physics-Inspired Global-Local Decoupling](https://mlsanity.com/paper/2606.25732/) (2026)
- [DPSF-Net: A Dual-Prior Spatial-Frequency Network for Real-World Remote Sensing Image Dehazing](https://mlsanity.com/paper/2609.06962/) (2026)

## Abstract (arXiv)

Currently, most single image dehazing models cannot run an ultra-high-resolution (UHD) image with a single GPU shader in real-time. To address the problem, we introduce the principle of infinite approximation of Taylor's theorem with the Laplace pyramid pattern to build a model which is capable of handling 4K hazy images in real-time. The N branch networks of the pyramid network correspond to the N constraint terms in Taylor's theorem. Low-order polynomials reconstruct the low-frequency information of the image (e.g. color, illumination). High-order polynomials regress the high-frequency information of the image (e.g. texture). In addition, we propose a Tucker reconstruction-based regularization term that acts on each branch network of the pyramid model. It further constrains the generation of anomalous signals in the feature space. Extensive experimental results demonstrate that our approach can not only run 4K images with haze in real-time on a single GPU (80FPS) but also has unparalleled interpretability. The developed method achieves state-of-the-art (SOTA) performance on two benchmarks (O/I-HAZE) and our updated 4KID dataset while providing the reliable groundwork for subsequent optimization schemes.