English

A New Low-Rank Tensor Model for Video Completion

Computer Vision and Pattern Recognition 2015-09-08 v1

Abstract

In this paper, we propose a new low-rank tensor model based on the circulant algebra, namely, twist tensor nuclear norm or t-TNN for short. The twist tensor denotes a 3-way tensor representation to laterally store 2D data slices in order. On one hand, t-TNN convexly relaxes the tensor multi-rank of the twist tensor in the Fourier domain, which allows an efficient computation using FFT. On the other, t-TNN is equal to the nuclear norm of block circulant matricization of the twist tensor in the original domain, which extends the traditional matrix nuclear norm in a block circulant way. We test the t-TNN model on a video completion application that aims to fill missing values and the experiment results validate its effectiveness, especially when dealing with video recorded by a non-stationary panning camera. The block circulant matricization of the twist tensor can be transformed into a circulant block representation with nuclear norm invariance. This representation, after transformation, exploits the horizontal translation relationship between the frames in a video, and endows the t-TNN model with a more powerful ability to reconstruct panning videos than the existing state-of-the-art low-rank models.

Keywords

Cite

@article{arxiv.1509.02027,
  title  = {A New Low-Rank Tensor Model for Video Completion},
  author = {Wenrui Hu and Dacheng Tao and Wensheng Zhang and Yuan Xie and Yehui Yang},
  journal= {arXiv preprint arXiv:1509.02027},
  year   = {2015}
}

Comments

8 pages, 11 figures, 1 table

R2 v1 2026-06-22T10:50:44.508Z