Abstract
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 which stabilizes the training and improves the restoration results. In the experiments, we 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 \url{this https URL}.
Abstract (translated)
本论文提出了一种用于一般图像恢复的随机微分方程(SDE)方法。其主要构造是mean-reverting SDE,它可以将高质量的图像转化为退化的副本,并以固定高斯噪声的均值状态来实现。通过模拟相应的逆时间SDE,我们可以恢复低质量图像的起源,而不需要依赖于任何特定任务的前知。至关重要的是,我们提出的mean-reverting SDE有一个 closed-form 的解决方案,这使得我们可以计算时间依赖的真实值得分,并使用神经网络学习它。我们还提出了一种最大似然目标,以学习最优逆路径,这可以稳定训练并改善恢复结果。在实验中,我们表明,我们提出的方法在图像去噪、去模糊和去雾方面实现了高度竞争的性能,在两个去噪数据集上树立了新的领先地位。最后,通过图像超分辨率、填充和去雾的定性结果,进一步证明了我们方法的通用适用性。代码可在 url{this https URL} 获取。
URL
https://arxiv.org/abs/2301.11699