PGL-Net: Efficient Real-World Dehazing via Physics-Inspired Global-Local Decoupling
Welcome to the official model repository for PGL-Net. This repository hosts the pre-trained weights and highly optimized deployment files for our efficient real-world image dehazing network.
📝 Project Overview
PGL-Net (Physics-Inspired Global-Local Decoupling Network) is a lightweight architecture that embeds physical inductive biases via operator-level emulation to address the challenging ill-posed problem of single image dehazing.
Unlike traditional methods that suffer from inaccurate parameter estimation or deep learning approaches that act as heavy "black boxes," PGL-Net explicitly decouples the dehazing process into two stages:
- Global Distribution Rectification: The Physics-Inspired Affine Fusion (PAF) module implicitly models transmission and airlight subtraction to rectify feature distributions globally.
- Local Structural Refinement: The Degradation-Aware Modulation (DAM) block adaptively restores locally variant details.
As a result, PGL-Net achieves superior restoration quality comparable to heavy Transformer models, but with only ~3% of the parameters.
- Paper: Efficient Real-World Dehazing via Physics-Inspired Global-Local Decoupling [Code]
- Task: Real-World Image Dehazing
- Model Variants: PGL-Net-T (Tiny), PGL-Net-S (Small)
🚀 Deployment-Ready Weights
To facilitate real-world applications and industrial deployment, we provide extensive exported weights across multiple inference backends. All files are organized and ready for immediate download.
Available Formats
- PyTorch (
.pk): Standard weights for research and fine-tuning.
- ONNX (
.onnx): Cross-platform deployment.
- TensorRT (
.engine): Ultra-low latency inference on NVIDIA GPUs.
- OpenVINO (
.bin / .xml): Optimized for Intel CPUs/GPUs.
- MNN (
.mnn): Lightweight deployment for mobile and edge devices.
Supported Datasets (Pre-trained Domains)
The weights are provided for models trained on standard real-world dehazing benchmarks:
RUDBRRSHID (Remote Sensing Dehazing)RW2AH
(Files are named following the pattern: {dataset}_pglnet_{size}.{format})
💻 How to Download and Use
You can easily download specific deployment files using the huggingface_hub Python library.
1from huggingface_hub import hf_hub_download
2
3# Example: Download the ONNX weights for PGL-Net-T trained on RW2AH
4file_path = hf_hub_download(
5 repo_id="klay11/PGL-Net",
6 filename="rw2ah_pglnet_t.onnx"
7)
8print(f"Model downloaded to: {file_path}")
📖 Citation
If you find our work or these weights useful in your research or deployment, please consider citing our paper:
1@article{qu2026efficient,
2 title = {Efficient Real-World Dehazing via Physics-Inspired Global-Local Decoupling},
3 author = {Qu, Yifei and Li, Ru and Chen, Junjie and Wu, Jinyuan},
4 journal = {arXiv preprint arXiv:2606.25732},
5 year = {2026}
6}
