Recent advancements in perception for autonomous driving are driven by deep learning. In
order to achieve robust and accurate scene understanding, autonomous vehicles are …

Recent advancements in self-driving cars, robotics, and remote sensing have widened the
range of applications for 3D Point Cloud (PC) data. This data format poses several new …

Semantic occupancy perception is essential for autonomous driving, as automated vehicles
require a fine-grained perception of the 3D urban structures. However, existing relevant …

In this work, we introduce OpenIns3D, a new 3D-input-only framework for 3D open-
vocabulary scene understanding. The OpenIns3D framework employs a “Mask-Snap …

Abstract We present the Dayton Annotated LiDAR Earth Scan (DALES) data set, a new large-
scale aerial LiDAR data set with over a half-billion hand-labeled points spanning 10 square …

3D semantic segmentation is one of the key tasks for autonomous driving system. Recently,
deep learning models for 3D semantic segmentation task have been widely researched, but …

Autonomous driving has rapidly developed and shown promising performance due to recent
advances in hardware and deep learning techniques. High-quality datasets are fundamental …

Although various 3D datasets with different functions and scales have been proposed
recently, it remains challenging for individuals to complete the whole pipeline of large-scale …

Semantic scene completion (SSC) aims to jointly estimate the complete geometry and
semantics of a scene, assuming partial sparse input. In the last years following the …

3D semantic segmentation is a fundamental task for robotic and autonomous driving
applications. Recent works have been focused on using deep learning techniques, whereas …