Dense Structure from a Dense Optical Flow Sequence

Abstract

This paper presents a structure-from-motion system which deliversdensestructure 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 and employing an eigen-based uncertainty representation, we can decrease these complexities fromO(N2) toO(N) for every frame, whereNis the number of pixels in the images. We also show that our new representation of structural information makes it easy to merge over a long image sequence even when no specific feature is tracked over multiple frames.