Dual diversified dynamical Gaussian process latent variable model for video repairing

Xiong, Hao, Liu, Tongliang, Tao, Dacheng and Shen, Heng Tao (2016) Dual diversified dynamical Gaussian process latent variable model for video repairing. IEEE Transactions on Image Processing, 25 8: 3626-3637. doi:10.1109/TIP.2016.2573581

Author Xiong, Hao
Liu, Tongliang
Tao, Dacheng
Shen, Heng Tao
Title Dual diversified dynamical Gaussian process latent variable model for video repairing
Journal name IEEE Transactions on Image Processing   Check publisher's open access policy
ISSN 1057-7149
Publication date 2016-08-01
Sub-type Article (original research)
DOI 10.1109/TIP.2016.2573581
Open Access Status Not yet assessed
Volume 25
Issue 8
Start page 3626
End page 3637
Total pages 12
Place of publication Piscataway, NJ, United States
Publisher Institute of Electrical and Electronics Engineers
Language eng
Formatted abstract
In this paper, we propose a dual diversified dynamical Gaussian process latent variable model (D3GPLVM) to tackle the video repairing issue. For preservation purposes, videos have to be conserved on media. However, storing on media, such as films and hard disks, can suffer from unexpected data loss, for instance, physical damage. So repairing of missing or damaged pixels is essential for better video maintenance. Most methods seek to fill in missing holes by synthesizing similar textures from local patches (the neighboring pixels), consecutive frames, or the whole video. However, these can introduce incorrect contexts, especially when the missing hole or number of damaged frames is large. Furthermore, simple texture synthesis can introduce artifacts in undamaged and recovered areas. To address aforementioned problems, we introduce two diversity encouraging priors to both of inducing points and latent variables for considering the variety in existing videos. In D3GPLVM, the inducing points constitute a smaller subset of observed data, while latent variables are a low-dimensional representation of observed data. Since they have a strong correlation with the observed data, it is essential that both of them can capture distinct aspects of and fully represent the observed data. The dual diversity encouraging priors ensure that the trained inducing points and latent variables are more diverse and resistant for context-aware and artifacts-free-based video repairing. The defined objective function in our proposed model is initially not analytically tractable and must be solved by variational inference. Finally, experimental testing results illustrate the robustness and effectiveness of our method for damaged video repairing.
Keyword DGPLVM
Diversity prior
Inducing points
Latect variable
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: HERDC Pre-Audit
School of Information Technology and Electrical Engineering Publications
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 4 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 4 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 11 Oct 2016, 11:56:12 EST by System User on behalf of Learning and Research Services (UQ Library)