论文标题
用于图像恢复问题的后置采样的正则条件gan
A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems
论文作者
论文摘要
在图像恢复问题中，人们试图从扭曲，不完整和/或噪声浪费的测量中推断出图像。此类问题在磁共振成像（MRI），计算机断层扫描，脱毛，超分辨率，介入，相位检索，图像到图像翻译和其他应用中出现。鉴于一组信号/测量对，我们不仅要做出一个良好的图像估计值。相反，我们的目标是快速，准确地从后部分布中采样。为此，我们提出了一个正规的条件瓦斯汀甘，每秒产生数十个高质量的后验样品。我们的正规化包括$ \ ell_1 $罚款和自适应加权的标准差奖励。使用定量评估指标，例如有条件的FRéchet成立距离，我们证明了我们的方法在多层MRI和大规模介绍应用中都会产生最新的后验样品。可以在此处找到我们模型的代码：https：//github.com/matt-bendel/rcgan
In image recovery problems, one seeks to infer an image from distorted, incomplete, and/or noise-corrupted measurements. Such problems arise in magnetic resonance imaging (MRI), computed tomography, deblurring, super-resolution, inpainting, phase retrieval, image-to-image translation, and other applications. Given a training set of signal/measurement pairs, we seek to do more than just produce one good image estimate. Rather, we aim to rapidly and accurately sample from the posterior distribution. To do this, we propose a regularized conditional Wasserstein GAN that generates dozens of high-quality posterior samples per second. Our regularization comprises an $\ell_1$ penalty and an adaptively weighted standard-deviation reward. Using quantitative evaluation metrics like conditional Fréchet inception distance, we demonstrate that our method produces state-of-the-art posterior samples in both multicoil MRI and large-scale inpainting applications. The code for our model can be found here: https://github.com/matt-bendel/rcGAN
