We present a near real-time (10Hz) method for 6-DoF tracking of an unknown object from a
monocular RGBD video sequence, while simultaneously performing neural 3D …

As a fundamental problem in computer vision, 3D point cloud registration (PCR) aims to
seek the optimal pose to align a point cloud pair. In this paper, we present a 3D registration …

Removing outlier correspondences is one of the critical steps for successful feature-based
point cloud registration. Despite the increasing popularity of introducing deep learning …

In this paper, we present a second order spatial compatibility (SC^ 2) measure based
method for efficient and robust point cloud registration (PCR), called SC^ 2-PCR. Firstly, we …

3D scene graphs have recently emerged as a powerful high-level representation of 3D
environments. A 3D scene graph describes the environment as a layered graph where …

Learning-based perception and prediction modules in modern autonomous driving systems
typically rely on expensive human annotation and are designed to perceive only a handful of …

Humans are able to form a complex mental model of the environment they move in. This
mental model captures geometric and semantic aspects of the scene, describes the …

Point cloud registration is a fundamental problem in 3D computer vision, graphics and
robotics. For the last few decades, existing registration algorithms have struggled in …