Rotation-invariant transformer for point cloud matching

H Yu, Z Qin, J Hou, M Saleh, D Li… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
The intrinsic rotation invariance lies at the core of matching point clouds with handcrafted
descriptors. However, it is widely despised by recent deep matchers that obtain the rotation …

Discriminative correspondence estimation for unsupervised rgb-d point cloud registration

C Yan, M Feng, Z Wu, Y Guo, W Dong… - … on Circuits and …, 2024‏ - ieeexplore.ieee.org
Point cloud registration is a fundamental task for estimating the rigid transformation matrix
between two point clouds, and is regarded as a prerequisite for downstream vision tasks …

Egosg: Learning 3d scene graphs from egocentric rgb-d sequences

C Zhang, X Yang, J Hou, K Kitani… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Constructing a 3D scene graph of an environment is essential for agents and smart glasses
assistants to develop an understanding of their surroundings and predict relationships …

HECPG: hyperbolic embedding and confident patch-guided network for point cloud matching

Y **e, J Zhu, S Li, N Hu, P Shi - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
As a fundamental problem in photogrammetry and remote sensing, terrestrial laser scanner
point cloud matching aims to seek a correspondence set that can match two partially …

Pcr-cg: Point cloud registration via deep explicit color and geometry

Y Zhang, J Yu, X Huang, W Zhou, J Hou - European Conference on …, 2022‏ - Springer
In this paper, we introduce PCR-CG: a novel 3D point cloud registration module explicitly
embedding the color signals into geometry representation. Different from the previous SOTA …

Deep learning-based low overlap point cloud registration for complex scenario: The review

Y Zhao, J Zhang, S Xu, J Ma - Information Fusion, 2024‏ - Elsevier
Most studies on point cloud registration have established the problem in the case of ideal
point cloud data. Although the state-of-the-art approaches have achieved amazing results …

Non-rigid shape registration via deep functional maps prior

P Jiang, M Sun, R Huang - Advances in Neural Information …, 2023‏ - proceedings.neurips.cc
In this paper, we propose a learning-based framework for non-rigid shape registra-tion
without correspondence supervision. Traditional shape registration techniques typically rely …

Spherenet: Learning a noise-robust and general descriptor for point cloud registration

G Zhao, Z Guo, X Wang, H Ma - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Point cloud registration aims to estimate a transformation that aligns point clouds collected
from different perspectives. In learning-based point cloud registration, a robust descriptor is …

Bilevel fusion with local and global cues for point cloud upsampling

Y Zhu, Z Zhang, X Cheng… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
This study focuses on point cloud upsampling, crucial in 3-D data processing but hindered
by current 3-D sensor limitations. Point clouds from RGB-D cameras and light detection and …

Diff-Reg: Diffusion Model in Doubly Stochastic Matrix Space for Registration Problem

Q Wu, H Jiang, L Luo, J Li, Y Ding, J **e… - European Conference on …, 2024‏ - Springer
Establishing reliable correspondences is essential for 3D and 2D-3D registration tasks.
Existing methods commonly leverage geometric or semantic point features to generate …