arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.01809cs.CV
收藏

基于CNN的投影梯度下降一致性图像重建

CNN-Based Projected Gradient Descent for Consistent Image Reconstruction

EPFL(洛桑联邦理工学院)

Harshit Gupta, Kyong Hwan Jin, Ha Q. Nguyen, Michael T. McCann, Michael Unser

摘要:

提出了一种新的图像重建方法,该方法用卷积神经网络(CNN)代替投影梯度下降(PGD)中的投影仪。作为高维(图像到图像)回归器训练的CNN最近已被用于有效地解决成像中的逆问题。然而,这些方法缺乏反馈机制来强制重建图像与测量一致。这对于逆问题至关重要,在生物医学成像中更是如此,其中重建用于诊断。在我们的方案中,梯度下降强制测量一致性,而CNN递归地将解决方案投影到更接近所需重建图像的空间。我们提供了一个正式的框架,以确保经典的PGD收敛到一个非凸约束最小二乘问题的局部极小。当投影仪被替换为CNN时,我们提出了一个放松的PGD,它总是收敛的。最后,我们提出了一个简单的计划,训练一个CNN像一个投影仪。我们的实验稀疏视图计算机断层扫描(CT)重建无噪声和有噪声的测量显示了改进的全变分(TV)的方法和最近的CNN为基础的技术。

英文摘要:

We present a new method for image reconstruction which replaces the projector in a projected gradient descent (PGD) with a convolutional neural network (CNN). CNNs trained as high-dimensional (image-to-image) regressors have recently been used to efficiently solve inverse problems in imaging. However, these approaches lack a feedback mechanism to enforce that the reconstructed image is consistent with the measurements. This is crucial for inverse problems, and more so in biomedical imaging, where the reconstructions are used for diagnosis. In our scheme, the gradient descent enforces measurement consistency, while the CNN recursively projects the solution closer to the space of desired reconstruction images. We provide a formal framework to ensure that the classical PGD converges to a local minimizer of a non-convex constrained least-squares problem. When the projector is replaced with a CNN, we propose a relaxed PGD, which always converges. Finally, we propose a simple scheme to train a CNN to act like a projector. Our experiments on sparse view Computed Tomography (CT) reconstruction for both noiseless and noisy measurements show an improvement over the total-variation (TV) method and a recent CNN-based technique.

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。

↑