Deblur, super-resolution, and inpainting using an efficient diffusion model with DiffPIR
Deblur, super-resolution, and inpainting using an efficient diffusion model with DiffPIR
Denoising Diffusion Models for Plug-and-Play Image Restoration
arXiv paper abstract https://arxiv.org/abs/2305.08995
arXiv PDF paper https://arxiv.org/pdf/2305.08995.pdf
GitHub https://github.com/yuanzhi-zhu/DiffPIR
Plug-and-play Image Restoration (IR) … a flexible and interpretable method for solving various inverse problems by utilizing any off-the-shelf denoiser as the implicit image prior.
… diffusion models … potential to serve as a generative denoiser prior to the plug-and-play IR methods remains to be further explored.
… other … diffusion models for image restoration … fail to achieve satisfactory results or … require an unacceptable number of Neural Function Evaluations (NFEs) during inference.
This paper proposes DiffPIR, which integrates the traditional plug-and-play method into the diffusion sampling framework.
Compared to plug-and-play IR methods that rely on discriminative Gaussian denoisers, DiffPIR is expected to inherit the generative ability of diffusion models.
Experimental … on three … IR tasks, including super-resolution, image deblurring, and inpainting, demonstrate … DiffPIR achieves state-of-the-art performance … with no more than 100 NFEs …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
