# Efficient Real-World Dehazing via Physics-Inspired Global-Local Decoupling

arXiv: https://arxiv.org/abs/2606.25732 · HTML: https://mlsanity.com/paper/2606.25732/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 51 of its 84 references that are in the map.
- First posted on arXiv 24 Jun 2026.

## Builds on (most cited first, 30 of 51)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (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)
- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [Vision Transformers for Single Image Dehazing](https://mlsanity.com/paper/2204.03883/) (2022)
- [GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing](https://mlsanity.com/paper/1908.03245/) (2019)
- [Densely Connected Pyramid Dehazing Network](https://mlsanity.com/paper/1803.08396/) (2018)
- [Gated Fusion Network for Single Image Dehazing](https://mlsanity.com/paper/1804.00213/) (2018)
- [NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images](https://mlsanity.com/paper/2005.03560/) (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)
- [DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention](https://mlsanity.com/paper/2301.04805/) (2023)
- [Gated Context Aggregation Network for Image Dehazing and Deraining](https://mlsanity.com/paper/1811.08747/) (2018)
- [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)
- [YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection](https://mlsanity.com/paper/2509.25164/) (2025)
- [Fourier Space Losses for Efficient Perceptual Image Super-Resolution](https://mlsanity.com/paper/2106.00783/) (2021)
- [RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors](https://mlsanity.com/paper/2304.03994/) (2023)
- [I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images](https://mlsanity.com/paper/1804.05091/) (2018)
- [You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network](https://mlsanity.com/paper/2006.16829/) (2020)
- [YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception](https://mlsanity.com/paper/2506.17733/) (2025)

## Abstract (arXiv)

Real-world single image dehazing is highly ill-posed due to spatially and spectrally varying scattering, while practical deployment demands lightweight and low-latency models. Existing approaches either rely on fragile physical inversion under simplified assumptions or adopt heavy blind architectures unsuitable for edge deployment. To overcome these limitations, we propose PGL-Net (Physics-Inspired Global-Local Decoupling Network), a lightweight framework that incorporates physical inductive biases via operator-level emulation, avoiding explicit parameter estimation. It decouples dehazing into global distribution rectification and local structural refinement. A Physics-Inspired Affine Fusion (PAF) module performs globally conditioned alignment across hierarchical skip connections to compensate for haze-induced bias, while a compact Degradation-Aware Modulation (DAM) block adaptively restores spatially and spectrally variant details through dynamic feature modulation. Extensive experiments on multiple real-world benchmarks demonstrate that PGL-Net achieves state-of-the-art restoration quality with significantly reduced complexity. Compared with the recent SOTA SGDN, the Tiny variant (PGL-Net-T) improves PSNR by up to 2.6dB and consistently enhances downstream object detection accuracy, while achieving over a 10x reduction in inference latency. Code is publicly available at: https://github.com/sc-30-bit/PGL-Net.