Multi-tensor Completion for Estimating Missing Values in Video Data
This addresses video in-painting for applications with multiple related datasets, but it is incremental as it extends single-dataset methods to multi-dataset scenarios.
The paper tackles the problem of video in-painting by proposing a method that exploits relationships among multiple datasets to improve data completion, showing significant performance gains, especially for very high missing percentages.
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.