Several deep learning methods for phase retrieval exist, but most of them fail on realistic data without precise support information. We propose a novel method based on single-instance deep generative prior that works well on complex-valued crystal data.

翻译：阶段检索有几种深层次的学习方法,但大多数方法没有准确的辅助信息,就以现实的数据为根据而失败。 我们建议采用基于单一系统之前深层基因化的新颖方法,该方法在复杂价值水晶数据上运作良好。