| --- |
| license: mit |
| pipeline_tag: image-to-image |
| tags: |
| - photography |
| - image restoration |
| - image enhancement |
| - computer vision |
| - multimodal |
| --- |
| |
| # InstructIR ✏️🖼️ |
|
|
| [High-Quality Image Restoration Following Human Instructions](https://arxiv.org/abs/2401.16468) (arxiv version) |
|
|
| [Marcos V. Conde](https://scholar.google.com/citations?user=NtB1kjYAAAAJ&hl=en), [Gregor Geigle](https://scholar.google.com/citations?user=uIlyqRwAAAAJ&hl=en), [Radu Timofte](https://scholar.google.com/citations?user=u3MwH5kAAAAJ&hl=en) |
|
|
| Computer Vision Lab, University of Wuerzburg | Sony PlayStation, FTG |
|
|
| ### TL;DR: quickstart |
| InstructIR takes as input an image and a human-written instruction for how to improve that image. The neural model performs all-in-one image restoration. InstructIR achieves state-of-the-art results on several restoration tasks including image denoising, deraining, deblurring, dehazing, and (low-light) image enhancement. |
|
|
| **🚀 You can start with the [demo tutorial](https://github.com/mv-lab/InstructIR/blob/main/demo.ipynb)** |
|
|
| <details> |
| <summary> <b> Abstract</b> (click me to read)</summary> |
| <p> |
| Image restoration is a fundamental problem that involves recovering a high-quality clean image from its degraded observation. All-In-One image restoration models can effectively restore images from various types and levels of degradation using degradation-specific information as prompts to guide the restoration model. In this work, we present the first approach that uses human-written instructions to guide the image restoration model. Given natural language prompts, our model can recover high-quality images from their degraded counterparts, considering multiple degradation types. Our method, InstructIR, achieves state-of-the-art results on several restoration tasks including image denoising, deraining, deblurring, dehazing, and (low-light) image enhancement. InstructIR improves +1dB over previous all-in-one restoration methods. Moreover, our dataset and results represent a novel benchmark for new research on text-guided image restoration and enhancement. |
| </p> |
| </details> |
|
|
| ### Contacts |
| For any inquiries contact Marcos V. Conde: <a href="mailto:marcos.conde@uni-wuerzburg.de">marcos.conde [at] uni-wuerzburg.de</a> |
|
|
|
|
| ### Citation BibTeX |
|
|
| ``` |
| @misc{conde2024instructir, |
| title={High-Quality Image Restoration Following Human Instructions}, |
| author={Marcos V. Conde, Gregor Geigle, Radu Timofte}, |
| year={2024}, |
| journal={arXiv preprint}, |
| } |
| ``` |
