Digital building representations enable and promote new forms of simulation, automation,
and information sharing. However, creating and maintaining these representations is …

Manhattan and Atlanta worlds hold for the structured scenes with only vertical and horizontal
dominant directions (DDs). To describe the scenes with additional sloping DDs, a mixture of …

Deep learning has improved vanishing point detection in images. Yet, deep networks
require expensive annotated datasets trained on costly hardware and do not generalize to …

The image lines projected from parallel 3D lines intersect at a common point called the
vanishing point (VP). Manhattan world holds for the scenes with three orthogonal VPs. In …

Image lines projected from parallel 3D lines intersect at a common point called the vanishing
point (VP). Manhattan world holds for the scenes with three orthogonal VPs. In Manhattan …

This letter presents an efficient and accurate simultaneous localization and mapping (SLAM)
system in man-made environments. The Manhattan world assumption is imposed, with …

We present a drift-free visual compass for estimating the three degrees of freedom (DoF)
rotational motion of a camera by recognizing structural regularities in a Manhattan world …

In man-made environments, most of the objects and structures are organized in the form of
orthogonal and parallel planes. These planes can be approximated by an Atlanta world …

In this work, we describe man-made structures via an appropriate structure assumption,
called Atlanta world, which contains a vertical direction (typically the gravity direction) and a …

Robustly fitting a linear model from outlier-contaminated data is an important and basic task
in many scientific fields, and it is often tackled by consensus set maximization. There have …