Image Restoration with Mean-Reverting Stochastic Differential Equations
This work addresses image restoration problems for computer vision applications, offering a novel method that is generalizable across tasks but appears incremental in its technical contributions.
The paper tackles general-purpose image restoration by proposing a mean-reverting stochastic differential equation (SDE) approach that transforms high-quality images into degraded versions and uses reverse-time SDE simulation to restore them without task-specific priors, achieving state-of-the-art results on two deraining datasets and competitive performance in deraining, deblurring, and denoising.
This paper presents a stochastic differential equation (SDE) approach for general-purpose image restoration. The key construction consists in a mean-reverting SDE that transforms a high-quality image into a degraded counterpart as a mean state with fixed Gaussian noise. Then, by simulating the corresponding reverse-time SDE, we are able to restore the origin of the low-quality image without relying on any task-specific prior knowledge. Crucially, the proposed mean-reverting SDE has a closed-form solution, allowing us to compute the ground truth time-dependent score and learn it with a neural network. Moreover, we propose a maximum likelihood objective to learn an optimal reverse trajectory that stabilizes the training and improves the restoration results. The experiments show that our proposed method achieves highly competitive performance in quantitative comparisons on image deraining, deblurring, and denoising, setting a new state-of-the-art on two deraining datasets. Finally, the general applicability of our approach is further demonstrated via qualitative results on image super-resolution, inpainting, and dehazing. Code is available at https://github.com/Algolzw/image-restoration-sde.