IEEE Trans Pattern Anal Mach Intell. 2016 Jul;38(7):1439-51. doi: 10.1109/TPAMI.2015.2481418. Epub 2015 Sep 23.
We describe a learning-based approach to blind image deconvolution. It uses a deep layered architecture, parts of which are borrowed from recent work on neural network learning, and parts of which incorporate computations that are specific to image deconvolution. The system is trained end-to-end on a set of artificially generated training examples, enabling competitive performance in blind deconvolution, both with respect to quality and runtime.
我们描述了一种基于学习的盲图像反卷积方法。它使用了一种深层架构，其中一部分是从最近的神经网络学习工作中借鉴而来，另一部分则包含了特定于图像反卷积的计算。该系统在一组人工生成的训练样本上进行端到端训练，使得在盲反卷积方面具有竞争力的性能，无论是在质量还是运行时间方面。
