Simultaneous localization and map** (SLAM) techniques are widely researched, since
they allow the simultaneous creation of a map and the sensors' pose estimation in an …

Autonomous driving vehicles require both a precise localization and map** solution in
different driving environment. In this context, Simultaneous Localization and Map** …

Visual SLAM (VSLAM) has been develo** rapidly due to its advantages of low-cost
sensors, the easy fusion of other sensors, and richer environmental information. Traditional …

The scene rigidity is a strong assumption in typical visual Simultaneous Localization and
Map** (vSLAM) algorithms. Such strong assumption limits the usage of most vSLAM in …

Most existing dynamic simultaneous localization and map** (SLAM) methods integrating
neural networks require high computational support and predefined categories of dynamic …

Current simultaneous localization and map** (SLAM) algorithms perform well in static
environments but easily fail in dynamic environments. Recent works introduce deep learning …

We present PVO, a novel panoptic visual odometry framework to achieve more
comprehensive modeling of the scene motion, geometry, and panoptic segmentation …

In this paper, we study the problem of 3D object detection from stereo images, in which the
key challenge is how to effectively utilize stereo information. Different from previous methods …

We present ClusterVO, a stereo Visual Odometry which simultaneously clusters and
estimates the motion of both ego and surrounding rigid clusters/objects. Unlike previous …