论文标题
从未配对的数据中学习以进行图像修复：变分贝叶斯方法
Learn from Unpaired Data for Image Restoration: A Variational Bayes Approach
论文作者
论文摘要
在实践中，收集配对的培训数据很困难，但是不合格的样本广泛存在。当前的方法旨在通过探索损坏的数据和清洁数据之间的关系来从未配对样本中生成综合培训数据。这项工作提出了Lud-vae，这是一种从边际分布中采样的数据中学习关节概率密度函数的深层生成方法。我们的方法基于一个经过精心设计的概率图形模型，在该模型中，干净和损坏的数据域在条件上是独立的。使用变异推理，我们最大化证据下限（ELBO）以估计关节概率密度函数。此外，我们表明在推理不变假设下没有配对样品的情况下，ELBO是可以计算的。该属性在未配对的环境中提供了我们方法的数学理由。最后，我们将我们的方法应用于现实世界的图像降解，超分辨率和低光图像增强任务，并使用Lud-Vae产生的合成数据训练模型。实验结果验证了我们方法比其他方法的优势。
Collecting paired training data is difficult in practice, but the unpaired samples broadly exist. Current approaches aim at generating synthesized training data from unpaired samples by exploring the relationship between the corrupted and clean data. This work proposes LUD-VAE, a deep generative method to learn the joint probability density function from data sampled from marginal distributions. Our approach is based on a carefully designed probabilistic graphical model in which the clean and corrupted data domains are conditionally independent. Using variational inference, we maximize the evidence lower bound (ELBO) to estimate the joint probability density function. Furthermore, we show that the ELBO is computable without paired samples under the inference invariant assumption. This property provides the mathematical rationale of our approach in the unpaired setting. Finally, we apply our method to real-world image denoising, super-resolution, and low-light image enhancement tasks and train the models using the synthetic data generated by the LUD-VAE. Experimental results validate the advantages of our method over other approaches.
