Multi-tensor Completion for Estimating Missing Values in Video Data

TL;DR

This paper introduces a novel multi-tensor completion method that leverages relationships among multiple related datasets to improve missing data estimation in videos, especially under high missing data scenarios.

Contribution

It proposes a new approach that exploits inter-dataset relationships for enhanced multi-video data completion, addressing limitations of single-dataset methods.

Findings

Significantly improves video in-painting performance

Effective with very high missing data percentages

Outperforms existing single-dataset methods

Abstract

Many tensor-based data completion methods aim to solve image and video in-painting problems. But, all methods were only developed for a single dataset. In most of real applications, we can usually obtain more than one dataset to reflect one phenomenon, and all the datasets are mutually related in some sense. Thus one question raised whether such the relationship can improve the performance of data completion or not? In the paper, we proposed a novel and efficient method by exploiting the relationship among datasets for multi-video data completion. Numerical results show that the proposed method significantly improve the performance of video in-painting, particularly in the case of very high missing percentage.