Dense Structure from a Dense Optical Flow Sequence

Abstract

This paper presents a structure-from-motion system which delivers dense structure information from a sequence of dense optical flows. Most traditional feature-based approaches cannot be extended to compute dense structure due to impractical computational complexity. We demonstrate that by decomposing uncertainty information into independent and correlated parts we can decrease these complexities from O (N2) to O(N), where is the number of pixels in the images. We also show that this dense structure-from-motion system requires only local optical flows, i.e. image matchings between two adjacent frames, instead of the tracking of features over a long sequence of frames.