Video Recovery via Low-Rank Tensor Completion with Spatio-Temporal Consistency
Hua Wang, Feiping Nie, Heng Huang
AAAI - 2014
Video completion is a computer vision technique to recover the missing values in video sequences by filling the unknown regions with the known information. In recent research, tensor completion, a generalization of matrix completion for higher order data, emerges as a new solution to estimate the missing information in video with the assumption that the video frames are homogenous and correlated. However, each video clip often stores the heterogeneous episodes and the correlations among all video frames are not high. Thus, the regular tenor completion methods are not suitable to recover the video missing values in practical applications. To solve this problem, we propose a novel spatially-temporally consistent tensor completion method for recovering the video missing data. Instead of minimizing the average of the trace norms of all matrices unfolded along each mode of a tensor data, we introduce a new smoothness regularization along video time direction to utilize the temporal information between consecutive video frames. Meanwhile, we also minimize the trace norm of each individual video frame to employ the spatial correlations among pixels. Different to previous tensor completion approaches, our new method can keep the spatio-temporal consistency in video and do not assume the global correlation in video frames. Thus, the proposed method can be applied to the general and practical video completion applications. Our method shows promising results in all evaluations on both 3D biomedical image sequence and video benchmark data sets.
Links
- View publications from Hua Wang
- View publications presented in AAAI
- View publications researching Matrix/Tensor Completion
- View publications applied to Computer Vision
- View publications applied to Medical Image Computing
Cite this paper
MLA
Wang, Hua, Feiping Nie, and Heng Huang. "Low-rank tensor completion with spatio-temporal consistency." Twenty-Eighth AAAI Conference on Artificial Intelligence. 2014.
BibTeX
@inproceedings{wang2014low,
title={Low-rank tensor completion with spatio-temporal consistency},
author={Wang, Hua and Nie, Feiping and Huang, Heng},
booktitle={Twenty-Eighth AAAI Conference on Artificial Intelligence},
year={2014}
}