eduzhai > Applied Sciences > Engineering >

Multi-Scale Deep Compressive Imaging

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 12 pages

Abstract: Recently, deep learning-based compressive imaging (DCI) has surpassed theconventional compressive imaging in reconstruction quality and faster runningtime. While multi-scale has shown superior performance over single-scale,research in DCI has been limited to single-scale sampling. Despite trainingwith single-scale images, DCI tends to favor low-frequency components similarto the conventional multi-scale sampling, especially at low subrate. From thisperspective, it would be easier for the network to learn multi-scale featureswith a multi-scale sampling architecture. In this work, we proposed amulti-scale deep compressive imaging (MS-DCI) framework which jointly learns todecompose, sample, and reconstruct images at multi-scale. A three-phaseend-to-end training scheme was introduced with an initial and two enhancereconstruction phases to demonstrate the efficiency of multi-scale sampling andfurther improve the reconstruction performance. We analyzed the decompositionmethods (including Pyramid, Wavelet, and Scale-space), sampling matrices, andmeasurements and showed the empirical benefit of MS-DCI which consistentlyoutperforms both conventional and deep learning-based approaches.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×