Pointr: Diverse point cloud completion with geometry-aware transformers

X Yu, Y Rao, Z Wang, Z Liu, J Lu… - Proceedings of the …, 2021 - openaccess.thecvf.com
Point clouds captured in real-world applications are often incomplete due to the limited
sensor resolution, single viewpoint, and occlusion. Therefore, recovering the complete point …

MV-DeepSDF: Implicit Modeling with Multi-Sweep Point Clouds for 3D Vehicle Reconstruction in Autonomous Driving

Y Liu, K Zhu, G Wu, Y Ren, B Liu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Reconstructing 3D vehicles from noisy and sparse partial point clouds is of great
significance to autonomous driving. Most existing 3D reconstruction methods cannot be …

3dsgrasp: 3d shape-completion for robotic grasp

SS Mohammadi, NF Duarte, D Dimou… - … on Robotics and …, 2023 - ieeexplore.ieee.org
Real-world robotic grasping can be done robustly if a complete 3D Point Cloud Data (PCD)
of an object is available. However, in practice, PCDs are often incomplete when objects are …

SCARP: 3D shape completion in ARbitrary poses for improved grasping

B Sen, A Agarwal, G Singh… - … on Robotics and …, 2023 - ieeexplore.ieee.org
Recovering full 3D shapes from partial observations is a challenging task that has been
extensively addressed in the computer vision community. Many deep learning methods …

Diffusion Models in 3D Vision: A Survey

Z Wang, D Li, R Jiang - arXiv preprint arXiv:2410.04738, 2024 - arxiv.org
In recent years, 3D vision has become a crucial field within computer vision, powering a
wide range of applications such as autonomous driving, robotics, augmented reality (AR) …

Dual-branch deep point cloud registration framework for unconstrained rotation

K Fu, Z Li, M Xu, X Luo, M Wang - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Learning-based rigid point cloud registration (RPCR) studies have made great progress
recently but most existing methods have a small convergence region and can only be used …

Dualgenerator: Information interaction-based generative network for point cloud completion

P Shi, H Cheng, X Han, Y Zhou… - IEEE Robotics and …, 2023 - ieeexplore.ieee.org
Point cloud completion estimates complete shapes from incomplete point clouds to obtain
higher-quality point cloud data. Most existing methods only consider global object features …

Mapping 3-D classroom seats based on partial object point cloud completion

E Zhou, AT Murray, J Baik - Cartography and Geographic …, 2024 - Taylor & Francis
D classroom seating information is of great significance in a host of planning contexts
including indoor navigation and facility management. Mapping classroom 3-D seats based …

NBV/NBC Planning Considering Confidence Obtained From Shape Completion Learning

R Liu, C Li, W Wan, J Pan… - IEEE Robotics and …, 2024 - ieeexplore.ieee.org
In this letter, we present a novel approach for planning an object's Next Best Views (NBV) so
that a depth camera can collect the object's surface point cloud and reconstruct its 3D model …

Linear Partial Gromov-Wasserstein Embedding

Y Bai, A Kothapalli, H Du, RD Martin… - arXiv preprint arXiv …, 2024 - arxiv.org
The Gromov Wasserstein (GW) problem, a variant of the classical optimal transport (OT)
problem, has attracted growing interest in the machine learning and data science …