当前位置: X-MOL 学术Signal Process. Image Commun. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
iPiano-Net: Nonconvex optimization inspired multi-scale reconstruction network for compressed sensing
Signal Processing: Image Communication ( IF 3.5 ) Pub Date : 2020-09-01 , DOI: 10.1016/j.image.2020.115989
Yueming Su , Qiusheng Lian

Compressed sensing (CS) aims to precisely reconstruct the original signal from under-sampled measurements, which is a typical ill-posed problem. Solving such a problem is challenging and generally needs to incorporate suitable priors about the underlying signals. Traditionally, these priors are hand-crafted and the corresponding approaches generally have limitations in expressive capacity. In this paper, a nonconvex optimization inspired multi-scale reconstruction network is developed for block-based CS, abbreviated as iPiano-Net, by unfolding the classic iPiano algorithm. In iPiano-Net, a block-wise inertial gradient descent interleaves with an image-level network-inducing proximal mapping to exploit the local block and global content information alternately. Therein, network-inducing proximal operators can be adaptively learned in each module, which can efficiently characterize image priors and improve the modeling capacity of iPiano-Net. Such learned image-level priors can suppress blocky artifacts and noises/corruptions while preserving the global information. Different from existing discriminative CS reconstruction models trained with specific measurement ratios, an effective single model is learned to handle CS reconstruction with several measurement ratios even the unseen ones. Experimental results demonstrate that the proposed approach is substantially superior to previous CS methods in terms of Peak Signal to Noise Ratio (PSNR) and visual quality, especially at low measurement ratios. Meanwhile, it is robust to noise while maintaining comparable execution speed.



中文翻译:

iPiano-Net:非凸面优化启发的多尺度重建网络,用于压缩传感

压缩感测(CS)旨在从欠采样测量中精确重建原始信号,这是一个典型的不适定问题。解决这样的问题是具有挑战性的,并且通常需要结合有关基础信号的适当先验。传统上,这些先验是手工制作的,相应的方法通常在表达能力上有局限性。在本文中,通过展开经典的iPiano算法,为基于块的CS开发了一个非凸优化启发式多尺度重建网络,缩写为iPiano-Net。在iPiano-Net中,逐块惯性梯度下降与图像级网络诱导的近端映射交错,以交替利用本地块和全局内容信息。其中,可以在每个模块中自适应地学习诱导网络的近端操作员,可以有效地表征图像先验并提高iPiano-Net的建模能力。这样学习的图像级先验可以抑制块状伪像和噪声/损坏,同时保留全局信息。与以特定的测量比率训练的现有判别CS重建模型不同,学习了有效的单个模型来处理具有多个测量比率(甚至是看不见的比率)的CS重建。实验结果表明,在峰值信噪比(PSNR)和视觉质量方面,尤其是在低测量比的情况下,该方法明显优于以前的CS方法。同时,它在保持相当的执行速度的同时,对噪声也很鲁棒。这样学习的图像级先验可以抑制块状伪像和噪声/损坏,同时保留全局信息。与以特定的测量比率训练的现有判别CS重建模型不同,学习了有效的单个模型来处理具有多个测量比率(甚至是看不见的比率)的CS重建。实验结果表明,在峰值信噪比(PSNR)和视觉质量方面,尤其是在低测量比的情况下,该方法明显优于以前的CS方法。同时,它在保持相当的执行速度的同时,对噪声也很鲁棒。这样学习的图像级先验可以抑制块状伪像和噪声/损坏,同时保留全局信息。与以特定的测量比率训练的现有判别CS重建模型不同,学习了有效的单个模型来处理具有多个测量比率(甚至是看不见的比率)的CS重建。实验结果表明,在峰值信噪比(PSNR)和视觉质量方面,尤其是在低测量比的情况下,该方法明显优于以前的CS方法。同时,它在保持相当的执行速度的同时,对噪声也很鲁棒。学习了一个有效的单一模型来处理具有多个测量比率(甚至是看不见的比率)的CS重建。实验结果表明,在峰值信噪比(PSNR)和视觉质量方面,尤其是在低测量比的情况下,该方法明显优于以前的CS方法。同时,它在保持相当的执行速度的同时,对噪声也很鲁棒。学习了一个有效的单一模型来处理具有多个测量比率(甚至是看不见的比率)的CS重建。实验结果表明,在峰值信噪比(PSNR)和视觉质量方面,尤其是在低测量比的情况下,该方法明显优于以前的CS方法。同时,它在保持相当的执行速度的同时,对噪声也很鲁棒。

更新日期:2020-09-14
down
wechat
bug