This article provides a comprehensive survey on pioneer and state-of-the-art 3D scene
geometry estimation methodologies based on single, two, or multiple images captured …

The digitization of Cultural Heritage is an important activity for the protection, management,
and conservation of structures of particular historical and architectural interest. In this …

Pose estimation is a crucial problem in several computer vision and robotics applications.
For the two-view scenario, the typical pipeline consists of finding point correspondences …

Omnidirectional media are becoming widespread with the increasing popularization of
devices for capture and visualization. Unlike traditional pinhole-based images …

Bundle adjustment (BA) is widely used in SLAM and SfM, which are key technologies in
Augmented Reality. For real-time SLAM and large-scale SfM, the efficiency of BA is of great …

Simultaneous localization and mapping (SLAM) is widely used in autonomous driving and
intelligent robot positioning and navigation. In order to overcome the defects of traditional …

In this paper, we propose a dense depth estimation pipeline for multiview 360∘ images. The
proposed pipeline leverages a spherical camera model that compensates for radial …

Monocular 360° depth estimation is an important and challenging task in computer vision
and 3D vision. Recently, deep neural networks have shown great abilities in estimating …

Multiple view geometry is a sub-field of computer vision dealing with the geometric relations
between a 3D scene and multiple cameras that project such scene into 2D images. This field …

Trajectory estimation as a fundamental aspect of mobile mapping system is divided into
several approaches including the importance of the motion model and description of the …