Efficient Image Restoration through Low-Rank Adaptation and Stable Diffusion XL
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914929547673600 |
|---|---|
| author | Zhao, Haiyang |
| author_facet | Zhao, Haiyang |
| contents | In this study, we propose an enhanced image restoration model, SUPIR, based on the integration of two low-rank adaptive (LoRA) modules with the Stable Diffusion XL (SDXL) framework. Our method leverages the advantages of LoRA to fine-tune SDXL models, thereby significantly improving image restoration quality and efficiency. We collect 2600 high-quality real-world images, each with detailed descriptive text, for training the model. The proposed method is evaluated on standard benchmarks and achieves excellent performance, demonstrated by higher peak signal-to-noise ratio (PSNR), lower learned perceptual image patch similarity (LPIPS), and higher structural similarity index measurement (SSIM) scores. These results underscore the effectiveness of combining LoRA with SDXL for advanced image restoration tasks, highlighting the potential of our approach in generating high-fidelity restored images. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_17060 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient Image Restoration through Low-Rank Adaptation and Stable Diffusion XL Zhao, Haiyang Computer Vision and Pattern Recognition In this study, we propose an enhanced image restoration model, SUPIR, based on the integration of two low-rank adaptive (LoRA) modules with the Stable Diffusion XL (SDXL) framework. Our method leverages the advantages of LoRA to fine-tune SDXL models, thereby significantly improving image restoration quality and efficiency. We collect 2600 high-quality real-world images, each with detailed descriptive text, for training the model. The proposed method is evaluated on standard benchmarks and achieves excellent performance, demonstrated by higher peak signal-to-noise ratio (PSNR), lower learned perceptual image patch similarity (LPIPS), and higher structural similarity index measurement (SSIM) scores. These results underscore the effectiveness of combining LoRA with SDXL for advanced image restoration tasks, highlighting the potential of our approach in generating high-fidelity restored images. |
| title | Efficient Image Restoration through Low-Rank Adaptation and Stable Diffusion XL |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.17060 |