Deep Data Consistency: a Fast and Robust Diffusion Model-based Solver for Inverse Problems
This work addresses the slow sampling speed and data consistency issues in diffusion models for inverse problems, which is incremental but improves practical applicability in domains like medical imaging or computational photography.
The authors tackled the challenge of balancing data consistency and realism in diffusion models for solving image inverse problems, achieving high-quality solutions with only 5 inference steps in 0.77 seconds on average and demonstrating robustness across datasets and noise levels.
Diffusion models have become a successful approach for solving various image inverse problems by providing a powerful diffusion prior. Many studies tried to combine the measurement into diffusion by score function replacement, matrix decomposition, or optimization algorithms, but it is hard to balance the data consistency and realness. The slow sampling speed is also a main obstacle to its wide application. To address the challenges, we propose Deep Data Consistency (DDC) to update the data consistency step with a deep learning model when solving inverse problems with diffusion models. By analyzing existing methods, the variational bound training objective is used to maximize the conditional posterior and reduce its impact on the diffusion process. In comparison with state-of-the-art methods in linear and non-linear tasks, DDC demonstrates its outstanding performance of both similarity and realness metrics in generating high-quality solutions with only 5 inference steps in 0.77 seconds on average. In addition, the robustness of DDC is well illustrated in the experiments across datasets, with large noise and the capacity to solve multiple tasks in only one pre-trained model.