Revisit Dictionary Learning for Video Compressive Sensing under the Plug-and-Play Framework

TL;DR

This paper introduces a shallow-learning-based denoiser using kernel singular value decomposition within the Plug-and-Play framework, significantly improving video compressive sensing reconstruction quality while maintaining efficiency.

Contribution

It revisits dictionary learning methods to develop a new denoiser for PnP, balancing quality, speed, and training complexity in video SCI reconstruction.

Findings

Achieves around 2 dB PSNR improvement over total variation baseline.

Demonstrates effectiveness across various datasets with both quantitative and qualitative results.

Provides a new baseline for video SCI reconstruction using PnP-KSVD.

Abstract

Aiming at high-dimensional (HD) data acquisition and analysis, snapshot compressive imaging (SCI) obtains the 2D compressed measurement of HD data with optical imaging systems and reconstructs HD data using compressive sensing algorithms. While the Plug-and-Play (PnP) framework offers an emerging solution to SCI reconstruction, its intrinsic denoising process is still a challenging problem. Unfortunately, existing denoisers in the PnP framework either suffer limited performance or require extensive training data. In this paper, we propose an efficient and effective shallow-learning-based algorithm for video SCI reconstruction. Revisiting dictionary learning methods, we empower the PnP framework with a new denoiser, the kernel singular value decomposition (KSVD). Benefited from the advent of KSVD, our algorithm retains a good trade-off among quality, speed, and training difficulty. On a variety of datasets, both quantitative and qualitative evaluations of our simulation results demonstrate the effectiveness of our proposed method. In comparison to a typical baseline using total variation, our method achieves around $2$ dB improvement in PSNR and 0.2 in SSIM. We expect that our proposed PnP-KSVD algorithm can serve as a new baseline for video SCI reconstruction.