Point cloud learning has lately attracted increasing attention due to its wide applications in
many areas, such as computer vision, autonomous driving, and robotics. As a dominating …

Autonomous vehicles were experiencing rapid development in the past few years. However,
achieving full autonomy is not a trivial task, due to the nature of the complex and dynamic …

Abstract 3D object detection is receiving increasing attention from both industry and
academia thanks to its wide applications in various fields. In this paper, we propose Point …

We present a novel and high-performance 3D object detection framework, named
PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds. Our …

Multi-view projection methods have demonstrated their ability to reach state-of-the-art
performance on 3D shape recognition. Those methods learn different ways to aggregate …

In this paper, we introduce the task of multi-view RGB-based 3D object detection as an end-
to-end optimization problem. To address this problem, we propose ImVoxelNet, a novel fully …

Abstract Monocular 3D Semantic Scene Completion (SSC) has garnered significant
attention in recent years due to its potential to predict complex semantics and geometry …

Transformers have shown superior performance on various computer vision tasks with their
capabilities to capture long-range dependencies. Despite the success, it is challenging to …

Many point cloud segmentation methods rely on transferring irregular points into a voxel-
based regular representation. Although voxel-based convolutions are useful for feature …

Semantic segmentation of 3D meshes is an important problem for 3D scene understanding.
In this paper we revisit the classic multiview representation of 3D meshes and study several …