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 …

Given a set of putative 3D-3D point correspondences, we aim to remove outliers and
estimate rigid transformation with 6 degrees of freedom (DOF). Simultaneously estimating …

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 …

Previous works on vanishing point detection usually use geometric prior for line segment
clustering. We find that image context can also contribute to accurate line classification …

Linear perspective cues deriving from regularities of the built environment can be used to
recalibrate both intrinsic and extrinsic camera parameters online, but these estimates can be …

In the field of vanishing point detection, previous works commonly relied on extracting and
clustering straight lines or classifying candidate points as vanishing points. This paper …

Simultaneous localization and mapping (SLAM) is a crucial technology for robot navigation,
3Dreconstruction, and virtual/augmented reality. While it has been widely studied for many …