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

High-quality 3D reconstruction is an important topic in computer graphics and computer
vision with many applications, such as robotics and augmented reality. The advent of …

Recent work has shown that CNN-based depth and ego-motion estimators can be learned
using unlabelled monocular videos. However, the performance is limited by unidentified …

Traditionally, 3D indoor scene reconstruction from posed images happens in two phases:
per-image depth estimation, followed by depth merging and surface reconstruction …

To autonomously navigate and plan interactions in real-world environments, robots require
the ability to robustly perceive and map complex, unstructured surrounding scenes. Besides …

We propose a method of learning suitable convolutional representations for camera pose
retrieval based on nearest neighbour matching and continuous metric learning-based …

Abstract Simultaneous Localization and Map** (SLAM) with dense representation plays a
key role in robotics, Virtual Reality (VR), and Augmented Reality (AR) applications. Recent …

Recent researches on robotics have shown significant improvement, spanning from
algorithms, mechanics to hardware architectures. Robotics, including manipulators, legged …

Previous online 3D dense reconstruction methods struggle to achieve the balance between
memory storage and surface quality, largely due to the usage of stagnant underlying …

Freehand gesture is an essential input modality for modern Augmented Reality (AR) user
experiences. However, develo** AR applications with customized hand interactions …