Diffusion Posterior Proximal Sampling for Image Restoration
This work addresses image restoration for applications like photography or medical imaging, offering an incremental improvement over existing diffusion-based methods.
The paper tackles the problem of over-smoothed results in diffusion-based image restoration by proposing a refined paradigm that selects samples consistent with measurements at each step and starts with measurement-informed initialization. The result is significantly enhanced performance with negligible extra computational cost, as validated by experiments.
Diffusion models have demonstrated remarkable efficacy in generating high-quality samples. Existing diffusion-based image restoration algorithms exploit pre-trained diffusion models to leverage data priors, yet they still preserve elements inherited from the unconditional generation paradigm. These strategies initiate the denoising process with pure white noise and incorporate random noise at each generative step, leading to over-smoothed results. In this paper, we present a refined paradigm for diffusion-based image restoration. Specifically, we opt for a sample consistent with the measurement identity at each generative step, exploiting the sampling selection as an avenue for output stability and enhancement. The number of candidate samples used for selection is adaptively determined based on the signal-to-noise ratio of the timestep. Additionally, we start the restoration process with an initialization combined with the measurement signal, providing supplementary information to better align the generative process. Extensive experimental results and analyses validate that our proposed method significantly enhances image restoration performance while consuming negligible additional computational resources.