| --- |
| library_name: pytorch |
| license: mit |
| pipeline_tag: image-to-image |
| tags: |
| - pytorch |
| - computer-vision |
| - image-super-resolution |
| - diffusion |
| --- |
| |
| # LPNSR: Prior-Enhanced Diffusion Image Super-Resolution via LR-Guided Noise Prediction |
|
|
| This repository contains the official model weights for **LPNSR**, a prior-enhanced efficient diffusion framework for image super-resolution (SR). |
|
|
| - **Paper:** [LPNSR: Prior-Enhanced Diffusion Image Super-Resolution via LR-Guided Noise Prediction](https://huggingface.co/papers/2603.21045) |
| - **GitHub Repository:** [Faze-Hsw/LPNSR](https://github.com/Faze-Hsw/LPNSR) |
|
|
| ## Introduction |
|
|
| LPNSR addresses the efficiency-quality trade-off in diffusion-based SR. While state-of-the-art frameworks like ResShift achieve efficient 4-step inference, they can suffer from performance degradation due to unconstrained random noise. LPNSR addresses this by: |
| - Replacing random Gaussian noise with an **LR-guided multi-input-aware noise predictor**, embedding structural priors into the reverse process. |
| - Mitigating initialization bias using a **high-quality pre-upsampling network** to optimize the diffusion starting point. |
| - Maintaining a compact 4-step sampling trajectory for high-quality, real-world super-resolution. |
|
|
| ## Features |
|
|
| - **Efficient Sampling**: Only 4 sampling steps required for high-quality super-resolution. |
| - **Noise Predictor**: Learns to predict optimal noise maps for partial diffusion initialization. |
| - **Real-world SR**: Designed to handle complex real-world degradations. |
| - **SwinIR Integration**: Optional SwinIR refinement for enhanced details. |
|
|
| ## Quick Start |
|
|
| To use these weights, clone the [official repository](https://github.com/Faze-Hsw/LPNSR) and follow the environment setup instructions. |
|
|
| ### Inference |
|
|
| Once the environment is set up and weights are placed in the `pretrained/` folder, run: |
|
|
| ```bash |
| python LPNSR/inference.py -i [image folder/image path] -o [output folder] |
| ``` |
|
|
| ### Online Demo |
|
|
| You can also launch a local Gradio web interface: |
|
|
| ```bash |
| python LPNSR/app.py |
| ``` |
|
|
| ## Citation |
|
|
| If you find this work useful, please cite: |
|
|
| ```bibtex |
| @article{lpnsr2026, |
| title={LPNSR: Prior-Enhanced Diffusion Image Super-Resolution via LR-Guided Noise Prediction}, |
| author={Huang, Shuwei and Liu, Shizhuo and Wei, Zijun}, |
| journal={arXiv preprint arXiv:2603.21045}, |
| year={2026}, |
| eprint={2603.21045}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.CV} |
| } |
| ``` |
|
|
| ## Acknowledgement |
|
|
| This project is based on [ResShift](https://github.com/zsyOAOA/ResShift), [BasicSR](https://github.com/XPixelGroup/BasicSR), [SwinIR](https://github.com/JingyunLiang/SwinIR), and [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN). |
