RORNet: Partial-to-partial registration network with reliable overlap** representations

Y Wu, Y Zhang, W Ma, M Gong, X Fan… - … on Neural Networks …, 2023‏ - ieeexplore.ieee.org
Three-dimensional point cloud registration is an important field in computer vision. Recently,
due to the increasingly complex scenes and incomplete observations, many partial-overlap …

Dual-graph attention convolution network for 3-D point cloud classification

CQ Huang, F Jiang, QH Huang… - … on Neural Networks …, 2022‏ - ieeexplore.ieee.org
Three-dimensional point cloud classification is fundamental but still challenging in 3-D
vision. Existing graph-based deep learning methods fail to learn both low-level extrinsic and …

Mvsalnet: Multi-view augmentation for rgb-d salient object detection

J Zhou, L Wang, H Lu, K Huang, X Shi, B Liu - European Conference on …, 2022‏ - Springer
RGB-D salient object detection (SOD) enjoys significant advantages in understanding 3D
geometry of the scene. However, the geometry information conveyed by depth maps are …

Rethinking training strategy in stereo matching

Z Rao, Y Dai, Z Shen, R He - IEEE Transactions on Neural …, 2022‏ - ieeexplore.ieee.org
In stereo matching, various learning-based approaches have shown impressive
performance in solving traditional difficulties on multiple datasets. While most progress is …

Vetaverse: A survey on the intersection of Metaverse, vehicles, and transportation systems

P Zhou, J Zhu, Y Wang, Y Lu, Z Wei, H Shi… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Since 2021, the term" Metaverse" has been the most popular one, garnering a lot of interest.
Because of its contained environment and built-in computing and networking capabilities, a …

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 …

Robust real-world point cloud registration by inlier detection

X Huang, Y Wang, S Li, G Mei, Z Xu, Y Wang… - Computer Vision and …, 2022‏ - Elsevier
Real-world point cloud registration is challenging because of large outliers in
correspondence search. The mixture variations, such as partial overlap, noise and cross …

Self-supervised point cloud representation learning via separating mixed shapes

C Sun, Z Zheng, X Wang, M Xu… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
The manual annotation for large-scale point clouds costs a lot of time and is usually
unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training …

Planeseg: Building a plug-in for boosting planar region segmentation

Z Zhang, S Chen, Z Wang… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Existing methods in planar region segmentation suffer the problems of vague boundaries
and failure to detect small-sized regions. To address these, this study presents an end-to …

An overlap estimation guided feature metric approach for real point cloud registration

F Zhang, L Zhang, T He, Y Sun, S Zhao, Y Zhang… - Computers & …, 2024‏ - Elsevier
Real point cloud registration, involving homologous and cross-source 3D data, poses
significant challenges such as partial overlap, high noise, density disparities, and scale …