Skip to main content
QUICK REVIEW

[论文解读] Neural Proximal Gradient Descent for Compressive Imaging

Morteza Mardani, Qingyun Sun|arXiv (Cornell University)|Jun 1, 2018
Sparse and Compressive Sensing Techniques被引用 117
一句话总结

本文将近端梯度迭代展开并用循环ResNet学习近端映射,实现比传统CS方法和非递归网络更快、数据可行的MRI重建以及更好的超分辨率。

ABSTRACT

Recovering high-resolution images from limited sensory data typically leads to a serious ill-posed inverse problem, demanding inversion algorithms that effectively capture the prior information. Learning a good inverse mapping from training data faces severe challenges, including: (i) scarcity of training data; (ii) need for plausible reconstructions that are physically feasible; (iii) need for fast reconstruction, especially in real-time applications. We develop a successful system solving all these challenges, using as basic architecture the recurrent application of proximal gradient algorithm. We learn a proximal map that works well with real images based on residual networks. Contraction of the resulting map is analyzed, and incoherence conditions are investigated that drive the convergence of the iterates. Extensive experiments are carried out under different settings: (a) reconstructing abdominal MRI of pediatric patients from highly undersampled Fourier-space data and (b) superresolving natural face images. Our key findings include: 1. a recurrent ResNet with a single residual block unrolled from an iterative algorithm yields an effective proximal which accurately reveals MR image details. 2. Our architecture significantly outperforms conventional non-recurrent deep ResNets by 2dB SNR; it is also trained much more rapidly. 3. It outperforms state-of-the-art compressed-sensing Wavelet-based methods by 4dB SNR, with 100x speedups in reconstruction time.

研究动机与目标

  • 在病态线性逆问题中推动快速、可信的重建。
  • 将物理数据一致性与学习得到的先验相结合。
  • 通过展开近端梯度迭代,开发神经近端梯度框架。
  • 分析学习到的近端的收缩性质与经验收敛性。
  • 在儿科MRI重建和自然图像超分辨率上进行评估。

提出的方法

  • 将近端梯度迭代建模为循环网络,以建模数据一致性更新。
  • 用多层神经网络(基于ResNet)建模近端算子。
  • 通过对训练集最小化经验风险进行端到端训练,采用混合损失(重建与测量一致性)。
  • 使用状态空间形式,s_{t+1}=g(x_t;y) 且 x_{t+1}=P_ψ(s_{t+1}),将数据保真与学习近端耦合。
  • 在近端网络中探索不同的激活掩码方案(D(z)),并通过 ResNet/DiracNet 变体解决梯度消失问题。

实验结果

研究问题

  • RQ1实现学习到的近端算子的循环神经网络能否提升欠采样逆问题的重建质量?
  • RQ2在MRI重建中重复一个小的近端块是否优于单一深度网络?
  • RQ3学习到的近端是否在经验上保持收缩性质,从而确保展开迭代的收敛?
  • RQ4神经近端方法在重建质量和速度方面与传统基于CS的方法及非递归深度网络相比如何?

主要发现

  • 一个在迭代中展开的带单个残差块(RB)的循环ResNet能够有效建模近端并揭示MR细节。
  • 循环架构在SNR上比非循环深度ResNet高约2 dB,且训练速度更快。
  • 该方法在SNR上比最先进的CS-WV方法高约4 dB,重建时间快高达100倍。
  • 增加迭代次数(T)可提升SNR和SSIM,但对于单次迭代而言,具有许多RB的非常深的网络不一定带来成比例的增益。
  • 对于MRI,10次迭代配1个RB在质量与计算之间提供了良好的权衡,便于实际临床使用。
  • 收缩分析表明,主导的收缩来自固定线性部分,学习到的近端贡献较小的扰动,后续迭代显示扰动效应衰减。

更好的研究,从现在开始

从论文设计到论文写作,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。