Video reconstruction based on Intrinsic Tensor Sparsity model

作者：

Highlights：

• We propose a tensor sparsity based reconstruction framework for video CS recovery exploiting the nonlocal structured sparsity via sparsity tensor approximation.

• We propose Gaussian Joint Sparsity (GJS) model to reconstruct the initial video sequence by employing the frame-to-frame similarity.

• An efficient ADMM algorithm is designed to solve the reconstruction problem based on ITS. What is more, the large matrix inverse problem is simplified by the block CS when solving the video signal with fixed sparse tensor.

摘要

•We propose a tensor sparsity based reconstruction framework for video CS recovery exploiting the nonlocal structured sparsity via sparsity tensor approximation.•We propose Gaussian Joint Sparsity (GJS) model to reconstruct the initial video sequence by employing the frame-to-frame similarity.•An efficient ADMM algorithm is designed to solve the reconstruction problem based on ITS. What is more, the large matrix inverse problem is simplified by the block CS when solving the video signal with fixed sparse tensor.

论文关键词：Compressive sensing,Gaussian mixture model,Joint sparsity,Intrinsic Tensor Sparsity,CACTI

论文评审过程：Received 28 June 2018, Revised 28 November 2018, Accepted 28 November 2018, Available online 27 December 2018, Version of Record 9 January 2019.

论文官网地址：https://doi.org/10.1016/j.image.2018.11.010