Optimal Representation of Multiple View Video

Marco Volino, Dan Casas, John Collomosse and Adrian Hilton

In Proceedings British Machine Vision Conference 2014


Multiple view video acquisition is widely used for reconstruction and free-viewpoint rendering of dynamic scenes by directly resampling from the captured images. This paper addresses the problem of optimally resampling and representing multiple view video to obtain a compact representation without loss of the view-dependent dynamic surface appearance. Spatio-temporal optimisation of the multiple view resampling is introduced to extract a coherent multi-layer texture map video. This resampling is combined with a surface-based optical flow alignment between views to correct for errors in geometric reconstruction and camera calibration which result in blurring and ghosting artefacts. The multi-view alignment and optimised resampling results in a compact representation with minimal loss of information allowing high-quality free-viewpoint rendering. Evaluation is performed on multiple view datasets for dynamic sequences of cloth, faces and people. The representation achieves >90% compression without significant loss of visual quality.


Video and Structure From Motion


Extended Abstract (PDF, 1 page, 2.1M)
Paper (PDF, 12 pages, 3.1M)
Supplemental Materials (ZIP, 7.6M)
Bibtex File



Marco Volino, Dan Casas, John Collomosse, and Adrian Hilton. Optimal Representation of Multiple View Video. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.


	title = {Optimal Representation of Multiple View Video},
	author = {Volino, Marco and Casas, Dan and Collomosse, John and Hilton, Adrian},
	year = {2014},
	booktitle = {Proceedings of the British Machine Vision Conference},
	publisher = {BMVA Press},
	editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
	doi = { http://dx.doi.org/10.5244/C.28.8 }