Update README.md

README.md

@@ -1,3 +1,106 @@
----
-license: cc-by-nc-sa-4.0
----
+---
+license: cc-by-nc-sa-4.0
+---
+# Resfusion
+
+Official model weights for **Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise**.
+
+This repository hosts pretrained checkpoints intended for **image restoration** tasks, including:
+
+- Shadow removal
+- Low-light image enhancement
+- Raindrop removal
+
+If you use this model or repository in research, please cite the original paper.
+
+---
+
+## Overview
+
+Resfusion is a diffusion-based image restoration framework that incorporates **prior residual noise patterns** into the denoising diffusion process. Compared with standard diffusion-based restoration pipelines, Resfusion is designed to better exploit degradation-aware residual structure for higher-quality restoration.
+
+This Hugging Face repository is intended to provide:
+
+- Pretrained model weights
+- Basic task descriptions
+- Inference guidance
+- Links to the original codebase and paper
+
+---
+
+## Supported checkpoints
+
+You can organize the released weights in this repository with names similar to the following:
+
+| Checkpoint | Task | Dataset |
+|---|---|---|
+| `resfusion-istd.ckpt` | Shadow removal | ISTD |
+| `resfusion-lol.ckpt` | Low-light enhancement | LOL |
+| `resfusion-raindrop.ckpt` | Raindrop removal | Raindrop |
+
+---
+
+## Model details
+
+- **Model type:** DDPM-based image restoration
+- **Framework:** PyTorch Lightning
+- **Primary use:** Paired image restoration
+- **Input:** Degraded image
+- **Output:** Restored image
+
+### Intended uses
+
+This model is intended for research and experimental applications in:
+
+- Image restoration benchmarking
+- Shadow removal
+- Low-light enhancement
+- Raindrop removal
+- Diffusion-based restoration studies
+
+---
+
+## Training data
+
+The original implementation supports the following datasets:
+
+- **ISTD** for shadow removal
+- **LOL** for low-light image enhancement
+- **Raindrop** for raindrop removal
+
+Please refer to the original project for exact data preparation, folder structure, and training configuration.
+
+---
+
+## Usage
+
+### Option 1: Use with the official codebase
+
+Please use the official Resfusion repository for inference and evaluation:
+
+- **Project repository:** `https://github.com/nkicsl/Resfusion`
+- **arXiv link:** `https://arxiv.org/abs/2311.14900`
+- **NeurIPS poster page:** `https://nips.cc/virtual/2024/poster/95696`
+
+Typical workflow:
+
+1. Clone the official repository.
+2. Create the environment from `environment.yaml`.
+3. Download the checkpoint from this Hugging Face repository.
+4. Place the checkpoint in your preferred checkpoint directory.
+5. Run the corresponding test script for your task.
+
+---
+
+## Citation
+
+If you use Resfusion in your work, please cite:
+
+```bibtex
+@inproceedings{li2024resfusion,
+  title={Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise},
+  author={Li, Sihao and Lu, Xingjian and Zhang, Jianzhuang},
+  booktitle={Advances in Neural Information Processing Systems},
+  year={2024}
+}
+```