Efficient Image Restoration through Low-Rank Adaptation and Stable Diffusion XL
This work addresses image restoration for applications requiring high-fidelity outputs, but it is incremental as it builds on existing methods like LoRA and SDXL.
The study tackled image restoration by integrating low-rank adaptation modules with Stable Diffusion XL, achieving improved quality and efficiency as shown by higher PSNR, lower LPIPS, and higher SSIM scores on standard benchmarks.
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.