RELD: Regularization by Latent Diffusion Models for Image Restoration
This work addresses image restoration problems for applications in imaging, but it is incremental as it builds on existing regularization and diffusion model principles.
The paper tackled image restoration tasks like denoising, deblurring, and super-resolution by integrating a Latent Diffusion Model into a variational framework, achieving competitive results with state-of-the-art methods, particularly in perceptual quality metrics.
In recent years, Diffusion Models have become the new state-of-the-art in deep generative modeling, ending the long-time dominance of Generative Adversarial Networks. Inspired by the Regularization by Denoising principle, we introduce an approach that integrates a Latent Diffusion Model, trained for the denoising task, into a variational framework using Half-Quadratic Splitting, exploiting its regularization properties. This approach, under appropriate conditions that can be easily met in various imaging applications, allows for reduced computational cost while achieving high-quality results. The proposed strategy, called Regularization by Latent Denoising (RELD), is then tested on a dataset of natural images, for image denoising, deblurring, and super-resolution tasks. The numerical experiments show that RELD is competitive with other state-of-the-art methods, particularly achieving remarkable results when evaluated using perceptual quality metrics.