Diversified dynamical Gaussian process latent variable model for video repair

Hao Xiong, Tongliang Liu, Dacheng Tao

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

1 Citation (Scopus)

Abstract

Videos can be conserved on different media. However, storing on media such as films and hard disks can suffer from unexpected data loss, for instance from physical damage. Repair of missing or damaged pixels is essential for video maintenance and preservation. Most methods seek to fill in missing holes by synthesizing similar textures from local or global frames. However, this 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 propose the diversified dynamical Gaussian process latent variable model (D2GPLVM) for considering the variety in existing videos and thus introducing a diversity encouraging prior to inducing points. The aim is to ensure that the trained inducing points, which are a smaller set of all observed undamaged frames, are more diverse and resistant for contextaware and artifacts-free based video repair. The defined objective function in our proposed model is initially not analytically tractable and must be solved by variational inference. Finally, experimental testing illustrates the robustness and effectiveness of our method for damaged video repair.

Original languageEnglish
Title of host publication30th AAAI Conference on Artificial Intelligence, AAAI 2016
PublisherAssociation for the Advancement of Artificial Intelligence
Pages3641-3647
Number of pages7
ISBN (Electronic)9781577357605
Publication statusPublished - 1 Jan 2016
Externally publishedYes
Event30th AAAI Conference on Artificial Intelligence, AAAI 2016 - Phoenix, United States
Duration: 12 Feb 201617 Feb 2016

Conference

Conference30th AAAI Conference on Artificial Intelligence, AAAI 2016
CountryUnited States
CityPhoenix
Period12/02/1617/02/16

    Fingerprint

Keywords

  • DGPLVM
  • inducing points
  • latect variable
  • diversity encouraging prior

Cite this

Xiong, H., Liu, T., & Tao, D. (2016). Diversified dynamical Gaussian process latent variable model for video repair. In 30th AAAI Conference on Artificial Intelligence, AAAI 2016 (pp. 3641-3647). Association for the Advancement of Artificial Intelligence.