Salvador J, Casas J. Multi-View Video Representation Based on Fast Monte Carlo Surface Reconstruction. IEEE Transactions on Image Processing. 2013;22(9):3342 - 3352.  (6.16 MB)

Abstract

This article provides an alternative solution for the costly representation of multi-view video data, which can be used for both rendering and scene analysis. First, a new, efficient Monte Carlo discrete surface reconstruction method for foreground objects with static background is presented, which outperforms volumetric techniques and is suitable for GPU environments. Some extensions are also presented, which allow speeding up the reconstruction by exploiting multi-resolution and temporal correlation. Then, a fast meshing algorithm is applied, which allows interpolating a continuous surface from the discrete reconstructed points. As shown by the experimental results, the original video frames can be approximated with high accuracy by projecting the reconstructed foreground objects onto the original viewpoints. Furthermore, the reconstructed scene can be easily projected onto any desired virtual viewpoint, simplifying thus the design of Free-Viewpoint Video applications. In our experimental results, we show that our techniques for reconstruction and meshing compare favorably to the state-of-the-art, and we also introduce a rule-of-thumb for effective application of the method with a good quality vs. representation cost trade-off.

Note: ranked 53 among the 100 most downloaded IEEE Xplore articles in July 2013 (Gormish, M., "Top Downloads in IEEE Xplore [Reader's Choice]," IEEE Signal Processing Magazine, vol.31, no.1, pp.8,9, Jan. 2014. doi: 10.1109/MSP.2013.2282791)