In this article, we deal with the problem of object detection on remote sensing images.
Previous researchers have developed numerous deep convolutional neural network (CNN) …

Non-rigid 3D shape correspondence aims to establish dense correspondences between two
non-rigidly deformed 3D shapes. However, the variability and symmetry of non-rigid shapes …

Point signature is a representation that describes the structural geometry of a point within a
neighborhood in 3D shapes. Conventional approaches apply a weight-sharing network, eg …

We propose a self-supervised method for partial point set registration. Although recently
proposed learning-based methods demonstrate impressive registration performance on full …

In this article, we propose a novel unsupervised method named GP-Aligner to address the
problem of groupwise nonrigid point set registration. Compared to previous nonlearning …

3D LiDAR place recognition plays a vital role in various robot applications' including robotic
navigation, autonomous driving, and simultaneous localization and map**. However …

Background: Large building fires are currently the most direct and serious type of fire that
causes property damage and casualties, and delayed evacuation is one of the important …

Point signature, a representation describing the structural neighborhood of a point in 3D
shapes, can be applied to establish correspondences between points in 3D shapes …

This thesis investigates the current state-of-the-art in registration of non-rigidly deforming
shapes. In particular, the problem of non-isometry is considered. First, a method to address …

View-based deep learning models have shown the capability to learn 3D shape descriptors
with superior performance on 3D shape recognition, classification, and retrieval. Most …