Qualitative HD image and video recovery via high-order tensor augmentation and completion

Pham Minh Hoang, Hoang Duong Tuan, Tran Thai Son, H. Vincent Poor

Research output: Contribution to journalArticlepeer-review

Abstract

This paper presents a new framework for severely distorted image and video recovery via tensor augmentation and completion. By considering the task of representing a matrix by a high-order-n tensor as that of encoding the matrix's 2-D indices (i, j) by n-digit words i1i2 . . . in, we develop a new high order tensor augmentation to cast a third order tensor of color images or video sequences containing missing pixels into a higher order tensor,which is similar to the ket augmentation of quantum physics, is capable of capturing all correlations and entanglements between entries of the original third order tensor. Accordingly, the resuling high-order tensor is completed by our previously developed parallel matrix factorization via tensor train decomposition. Simulations are provided to show the clear advantages of our approach in enhancing important metrics of visual quality such as relative square error and structural similarity index in image and video processing that help to achieve high recovery rates even for high-definition images and videos with 95% missing pixels.

Original languageEnglish (US)
Article number9281351
Pages (from-to)688-701
Number of pages14
JournalIEEE Journal on Selected Topics in Signal Processing
Volume15
Issue number3
DOIs
StatePublished - Apr 2021

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering

Keywords

  • Color image and video recovery
  • high order tensor augmentation
  • image concatenation
  • tensor completion
  • tensor train rank

Fingerprint

Dive into the research topics of 'Qualitative HD image and video recovery via high-order tensor augmentation and completion'. Together they form a unique fingerprint.

Cite this