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 2005.06001eess.IVcs.LGstat.ML
收藏

用于成像逆问题的深度学习技术

Deep Learning Techniques for Inverse Problems in Imaging

Rice University(莱斯大学);University of Texas at Austin(德克萨斯大学奥斯汀分校);University of Chicago(芝加哥大学);Stanford University(斯坦福大学)

Gregory Ongie, Ajil Jalal, Christopher A. Metzler, Richard G. Baraniuk, Alexandros G. Dimakis, Rebecca Willett

摘要:

机器学习领域的最新研究表明,深度神经网络可用于解决计算成像中出现的各种逆问题。我们探讨了这一新兴领域的中心流行主题,并提出了一个分类法,可用于对不同的问题和重建方法进行分类。我们的分类是沿着两个中心轴组织的:(1)前向模型是否已知,以及在训练和测试中使用的程度,以及(2)学习是否有监督或无监督,即,训练是否依赖于对匹配的地面实况图像和测量对的访问。我们还讨论了与这些不同的重建方法,警告和常见的故障模式,加上开放的问题和未来工作的途径相关的权衡。

英文摘要:

Recent work in machine learning shows that deep neural networks can be used to solve a wide variety of inverse problems arising in computational imaging. We explore the central prevailing themes of this emerging area and present a taxonomy that can be used to categorize different problems and reconstruction methods. Our taxonomy is organized along two central axes: (1) whether or not a forward model is known and to what extent it is used in training and testing, and (2) whether or not the learning is supervised or unsupervised, i.e., whether or not the training relies on access to matched ground truth image and measurement pairs. We also discuss the trade-offs associated with these different reconstruction approaches, caveats and common failure modes, plus open problems and avenues for future work.

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。

↑