Recently, deep learning-based compressive imaging (DCI) has surpassed the conventional compressive imaging in reconstruction quality and faster running time. While multi-scale has shown superior performance over single-scale, research in DCI has been limited to single-scale sampling. Despite training with single-scale images, DCI tends to favor low-frequency components similar to the conventional multi-scale sampling, especially at low subrate. From this perspective, it would be easier for the network to learn multi-scale features with a multi-scale sampling architecture. In this work, we proposed a multi-scale deep compressive imaging (MS-DCI) framework which jointly learns to decompose, sample, and reconstruct images at multi-scale. A three-phase end-to-end training scheme was introduced with an initial and two enhance reconstruction phases to demonstrate the efficiency of multi-scale sampling and further improve the reconstruction performance. We analyzed the decomposition methods (including Pyramid, Wavelet, and Scale-space), sampling matrices, and measurements and showed the empirical benefit of MS-DCI which consistently outperforms both conventional and deep learning-based approaches.

中文翻译：

---

多尺度深度压缩成像

最近，基于深度学习的压缩成像（DCI）在重建质量和更快的运行时间方面已经超越了传统的压缩成像。虽然多尺度表现出优于单尺度的性能，但 DCI 的研究仅限于单尺度采样。尽管使用单尺度图像进行训练，但 DCI 倾向于支持类似于传统多尺度采样的低频分量，尤其是在低子速率下。从这个角度来看，网络更容易学习具有多尺度采样架构的多尺度特征。在这项工作中，我们提出了一种多尺度深度压缩成像 (MS-DCI) 框架，该框架共同学习在多尺度下分解、采样和重建图像。引入了具有初始和两个增强重建阶段的三阶段端到端训练方案，以证明多尺度采样的效率并进一步提高重建性能。我们分析了分解方法（包括金字塔、小波和尺度空间）、采样矩阵和测量，并展示了 MS-DCI 的经验优势，它始终优于传统和基于深度学习的方法。