论文标题
优化生成模型的中间表示
Optimizing Intermediate Representations of Generative Models for Phase Retrieval
论文作者
论文摘要
相位检索是从仅尺度测量值重建图像的问题。在许多实际应用中，问题不确定。当训练数据可用时，生成模型允许在较低维的潜在空间中进行优化，从而将解决方案设置为可以由生成模型合成的图像。但是，并非所有可能的解决方案都在发电机的范围内。相反，它们的代表有一些错误。为了减少相位检索的上下文中的这种表示误差，我们首先利用了中间层优化（ILO）的新变化来扩展发电机的范围，同时仍会产生与训练数据一致的图像。其次，我们介绍了新的初始化方案，以进一步提高重建的质量。通过有关傅立叶相检索问题和彻底消融研究的广泛实验，我们可以展示我们修改的ILO和新的初始化方案的好处。此外，我们分析了方法在高斯阶段检索问题上的性能。
Phase retrieval is the problem of reconstructing images from magnitude-only measurements. In many real-world applications the problem is underdetermined. When training data is available, generative models allow optimization in a lower-dimensional latent space, hereby constraining the solution set to those images that can be synthesized by the generative model. However, not all possible solutions are within the range of the generator. Instead, they are represented with some error. To reduce this representation error in the context of phase retrieval, we first leverage a novel variation of intermediate layer optimization (ILO) to extend the range of the generator while still producing images consistent with the training data. Second, we introduce new initialization schemes that further improve the quality of the reconstruction. With extensive experiments on the Fourier phase retrieval problem and thorough ablation studies, we can show the benefits of our modified ILO and the new initialization schemes. Additionally, we analyze the performance of our approach on the Gaussian phase retrieval problem.
