Arbitrary-steps Image Super-resolution via Diffusion Inversion
This provides a flexible and efficient solution for image enhancement tasks, though it is incremental in improving existing diffusion-based super-resolution techniques.
The study tackled image super-resolution by using diffusion inversion to leverage pre-trained diffusion models, achieving superior or comparable performance to state-of-the-art methods with as few as one sampling step.
This study presents a new image super-resolution (SR) technique based on diffusion inversion, aiming at harnessing the rich image priors encapsulated in large pre-trained diffusion models to improve SR performance. We design a Partial noise Prediction strategy to construct an intermediate state of the diffusion model, which serves as the starting sampling point. Central to our approach is a deep noise predictor to estimate the optimal noise maps for the forward diffusion process. Once trained, this noise predictor can be used to initialize the sampling process partially along the diffusion trajectory, generating the desirable high-resolution result. Compared to existing approaches, our method offers a flexible and efficient sampling mechanism that supports an arbitrary number of sampling steps, ranging from one to five. Even with a single sampling step, our method demonstrates superior or comparable performance to recent state-of-the-art approaches. The code and model are publicly available at https://github.com/zsyOAOA/InvSR.