基于Langevin动力学的线性传感系统自适应采样
Adaptive Sampling for Linear Sensing Systems via Langevin Dynamics
摘要:
感测系统中的自适应或动态信号采样可以基于所获取的信号来调整后续采样策略,从而潜在地提高图像质量和速度。提出了一种基于贪婪方差缩减和随机梯度Langevin动力学(SGLD)的贝叶斯自适应采样方法。所涉及的图像先验可以是基于分析或神经网络的。值得注意的是,学习的图像先验知识很好地推广到具有与训练数据集不同的统计数据的分布外测试用例。作为一个现实世界的验证,该方法被应用到加速磁共振成像(MRI)的采集。与非自适应采样相比,该方法有效地提高了图像质量2-3 dB的峰值信噪比,并改善了细微细节的恢复。
英文摘要:
Adaptive or dynamic signal sampling in sensing systems can adapt subsequent sampling strategies based on acquired signals, thereby potentially improving image quality and speed. This paper proposes a Bayesian method for adaptive sampling based on greedy variance reduction and stochastic gradient Langevin dynamics (SGLD). The image priors involved can be either analytical or neural network-based. Notably, the learned image priors generalize well to out-of-distribution test cases that have different statistics than the training dataset. As a real-world validation, the method is applied to accelerate the acquisition of magnetic resonance imaging (MRI). Compared to non-adaptive sampling, the proposed method effectively improved the image quality by 2-3 dB in PSNR, and improved the restoration of subtle details.
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。