Convolutional neural networks (CNN) are limited by the lack of capability to handle geometric
information due to the fixed grid kernel structure. The availability of depth data enables …

We introduce Similarity Group Proposal Network (SGPN), a simple and intuitive deep
learning framework for 3D object instance segmentation on point clouds. SGPN uses a single …

Recent advances in convolutional neural networks have shown promising results in 3D
shape completion. But due to GPU memory limitations, these methods can only produce low-…

Reconstructing 3D shapes from single-view images has been a long-standing research
problem. In this paper, we present DISN, a Deep Implicit Surface Net-work which can generate a …

Point clouds are an efficient data format for 3D data. However, existing 3D segmentation
methods for point clouds either do not model local dependencies or require added computations…

Recently, the capability of character-level evaluation measures for machine translation
output has been confirmed by several metrics. This work proposes translation edit rate on …

Applications in virtual and augmented reality create a demand for rapid creation and easy
access to large sets of 3D models. An effective way to address this demand is to edit or deform …

3D object detection in point clouds is a core component for modern robotics and autonomous
driving systems. A key challenge in 3D object detection comes from the inherent sparse …

In autonomous driving, a LiDAR-based object detector should perform reliably at different
geographic locations and under various weather conditions. While recent 3D detection …

The detection of 3D objects from LiDAR data is a critical component in most autonomous
driving systems. Safe, high speed driving needs larger detection ranges, which are enabled by …