Update README.md

README.md

@@ -1,3 +1,65 @@
 ---
-license: mit
+license: apache-2.0
+tags:
+- image-dehazing
+- image-restoration
+- vision-transformer
+- transformer
+- low-level-vision
+- pytorch
+pipeline_tag: image-to-image
 ---
+
+# ED-Former: Efficient Dehazing Transformer with Attention-Adaptive Feed-Forward Network
+
+<div align="center">
+
+[![Paper](https://img.shields.io/badge/Paper-ScienceDirect-blue.svg)](https://www.sciencedirect.com/science/article/abs/pii/S0923596526001578)
+[![GitHub](https://img.shields.io/badge/GitHub-Repository-black?logo=github)](https://github.com/2697166190a-beep/ED-Former)
+[![License](https://img.shields.io/badge/License-Apache%202.0-green.svg)](https://opensource.org/licenses/Apache-2.0)
+
+</div>
+
+Official model weights and implementation details for **ED-Former**, published in ***Signal Processing: Image Communication***.
+
+---
+
+## 🌟 Highlights & Model Specs
+
+- **Attention-Adaptive Feed-Forward Network (AA-FFN)**: Dynamically refines feature representation while drastically cutting down computational overhead.
+- **Ultra Lightweight & Fast**: Only **0.866 M** parameters and **7.36 G MACs** (evaluated on 256×256 input size).
+- **State-of-the-Art Performance**: Achieves **38.21 dB PSNR** on SOTS-Indoor and **39.61 dB PSNR** on RS-Haze.
+
+---
+
+## 📊 Benchmark Results
+
+Quantitative evaluation across multiple standard synthetic and real-world dehazing benchmarks:
+
+| Benchmark Dataset | PSNR (dB) ↑ | SSIM ↑ | Model Weights |
+| :--- | :---: | :---: | :---: |
+| **SOTS-indoor (RESIDE-IN)** | **38.21** | **0.9942** | [Download](./) |
+| **SOTS-outdoor (RESIDE-OUT)** | **33.92** | **0.9827** | [Download](./) |
+| **RS-Haze** | **39.61** | **0.9715** | [Download](./) |
+| **O-HAZE (zero-shot)** | **15.78** | **0.7020** | [Download](./) |
+
+### ⚡ Computational Efficiency:
+- **Parameters (#Params)**: `0.866 M`
+- **Computational Cost (#MACs)**: `7.36 G` (for $256 \times 256$ input)
+
+---
+
+## 🚀 Quick Start & Inference
+
+Full training, testing scripts, and dataset setups are available at our **[GitHub Repository](https://github.com/2697166190a-beep/ED-Former)**.
+
+```bash
+# 1. Clone the repository
+git clone https://github.com/2697166190a-beep/ED-Former.git
+cd ED-Former
+
+# 2. Install dependencies
+pip install -r requirements.txt
+
+# 3. Run single image dehazing inference
+python test.py --input_dir ./demo/hazy_images/ --weights ./weights/ed_former_sots.pth --output_dir ./results/