计算机科学
压缩传感
启发式
人工神经网络
降噪
巨量平行
消息传递
噪音(视频)
实施
算法
图像(数学)
稀疏矩阵
人工智能
并行计算
计算机工程
物理
高斯分布
量子力学
程序设计语言
作者
Christopher A. Metzler,Ali Mousavi,Richard G. Baraniuk
摘要
Compressive image recovery is a challenging problem that requires fast and accurate algorithms. Recently, neural networks have been applied to this problem with promising results. By exploiting massively parallel GPU processing architectures and oodles of training data, they can run orders of magnitude faster than existing techniques. However, these methods are largely unprincipled black boxes that are difficult to train and often-times specific to a single measurement matrix. It was recently demonstrated that iterative sparse-signal-recovery algorithms can be ``unrolled’' to form interpretable deep networks. Taking inspiration from this work, we develop a novel neural network architecture that mimics the behavior of the denoising-based approximate message passing (D-AMP) algorithm. We call this new network {\em Learned} D-AMP (LDAMP). The LDAMP network is easy to train, can be applied to a variety of different measurement matrices, and comes with a state-evolution heuristic that accurately predicts its performance. Most importantly, it outperforms the state-of-the-art BM3D-AMP and NLR-CS algorithms in terms of both accuracy and run time. At high resolutions, and when used with sensing matrices that have fast implementations, LDAMP runs over $50\times$ faster than BM3D-AMP and hundreds of times faster than NLR-CS.
科研通智能强力驱动
Strongly Powered by AbleSci AI