arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1907.11713eess.IVcs.LG
收藏

学习合成:低光子计数下的鲁棒相位恢复

Learning to Synthesize: Robust Phase Retrieval at Low Photon counts

Massachusetts Institute of Technology(麻省理工学院);Singapore-MIT Alliance for Research and Technology (SMART) Centre(新加坡-麻省理工学院研究与技术联盟中心);SenseTime Research(商汤科技研究院);Omnisens SA(Omnisens公司)

Mo Deng, Shuai Li, Alexandre Goy, Iksung Kang, George Barbastathis

摘要:

通过深度学习[Barbastathis et al,2019]获得的反问题解决方案的质量受到从训练阶段提供的示例中学习到的先验性质的限制。在定量相位恢复的情况下[Sinha et al,2017,Goy et al,2019],特别是在训练数据库中代表性不足的空间频率,通常在高频带,往往在重建中被抑制。已经提出了特别的解决方案,例如在示例中预放大高空间频率[Li等人,2018];然而,虽然该策略提高了分辨率,但它也导致了高频伪影以及重建中的低频失真。在这里,我们提出了一种新的方法,分别学习如何处理两个频段,低和高,也学习如何合成这两个波段到全波段重建。我们表明,这种“学习合成”(LS)方法产生高空间分辨率和无伪影的相位重建;并且它对高噪声条件也有弹性,例如在非常低的光子通量的情况下。除了定量相位恢复的问题之外,LS方法原则上适用于任何逆问题,其中正向算子不均匀地处理不同的频段,即不适定。

英文摘要:

The quality of inverse problem solutions obtained through deep learning [Barbastathis et al, 2019] is limited by the nature of the priors learned from examples presented during the training phase. In the case of quantitative phase retrieval [Sinha et al, 2017, Goy et al, 2019], in particular, spatial frequencies that are underrepresented in the training database, most often at the high band, tend to be suppressed in the reconstruction. Ad hoc solutions have been proposed, such as pre-amplifying the high spatial frequencies in the examples [Li et al, 2018]; however, while that strategy improves resolution, it also leads to high-frequency artifacts as well as low-frequency distortions in the reconstructions. Here, we present a new approach that learns separately how to handle the two frequency bands, low and high; and also learns how to synthesize these two bands into the full-band reconstructions. We show that this "learning to synthesize" (LS) method yields phase reconstructions of high spatial resolution and artifact-free; and it is also resilient to high-noise conditions, e.g. in the case of very low photon flux. In addition to the problem of quantitative phase retrieval, the LS method is applicable, in principle, to any inverse problem where the forward operator treats different frequency bands unevenly, i.e. is ill-posed.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑