GitHub

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on textual descriptions, which is essential for applications like augmented reality and robotics. Traditional 3DVG approaches rely ...
IEEE

Learning Visual-Inertial Odometry With Robocentric Iterated Extended Kalman Filter

Abstract: In recent years, deep learning methodologies have been increasingly applied to the intricate challenges of visual-inertial odometry (VIO), especially in scenarios with rapid movements and ...
GitHub

Liberty Tools for Visual Studio Code

Note: Requires Visual Studio Code 1.78.0 or later, and Java 17 or later. This page provides an overview of Liberty Tools for Visual Studio Code. For minimum requirements information and detailed ...
IEEE

LatentBKI: Open-Dictionary Continuous Mapping in Visual-Language Latent Spaces With Quantifiable Uncertainty

Abstract: This letter introduces a novel probabilistic mapping algorithm, LatentBKI, which enables open-vocabulary mapping with quantifiable uncertainty. Traditionally, semantic mapping algorithms ...