Extracting vanishing points across multiple views

The realization that we see lines known to be parallel in space as lines that appear to converge in a corresponding vanishing point has led to techniques employed by artists since at least the Renaissance to render a credible impression of perspective. More recently, it has also led to techniques for recovering information embedded in images pertaining to the geometry of their underlying scene. In this paper, we explore the extraction of vanishing points in the aim of facilitating the reconstruction of Manhattan-world scenes. In departure from most vanishing point extraction methods, ours extracts a constellation of vanishing points corresponding, respectively, to the scene's two or three dominant pairwise-orthogonal orientations by integrating information across multiple views rather than from a single image alone. What makes a multiple-view approach attractive is that in addition to increasing robustness to segments that do not correspond to any of the three dominant orientations, robustness is also increased with respect to inaccuracies in the extracted segments themselves.