Deep learning-based 3D point cloud classification: A systematic survey and outlook
In recent years, point cloud representation has become one of the research hotspots in the
field of computer vision, and has been widely used in many fields, such as autonomous …
field of computer vision, and has been widely used in many fields, such as autonomous …
3D person re-identification based on global semantic guidance and local feature aggregation
Person re-identification (Re-ID) has played an extremely crucial role in ensuring social
safety and has attracted considerable research attention. 3D shape information is an …
safety and has attracted considerable research attention. 3D shape information is an …
A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation
Point cloud analysis has a wide range of applications in many areas such as computer
vision, robotic manipulation, and autonomous driving. While deep learning has achieved …
vision, robotic manipulation, and autonomous driving. While deep learning has achieved …
Real-time semantic segmentation of point clouds based on an attention mechanism and a sparse tensor
A 3D point cloud is one of the main data sources for robot environmental cognition and
understanding. Due to the limited computation and memory capacities of the robotic …
understanding. Due to the limited computation and memory capacities of the robotic …
Mdcsnet: multi-scale dynamic spatial information fusion with criticality sampling for point cloud classification
P Xia, S Tian, L Yu, X Fan, Z Zhu, H Dong, N Qu… - The Journal of …, 2025 - Springer
Point cloud classification is crucial in the processing and analysis of three-dimensional data.
However, the irregularities and disorders inherent in point cloud data pose significant …
However, the irregularities and disorders inherent in point cloud data pose significant …
A Method of Curve Reconstruction Based on Point Cloud Clustering and PCA
K Peng, J Tan, G Zhang - Symmetry, 2022 - mdpi.com
In many application fields (closed curve noise data reconstruction, time series data fitting,
image edge smoothing, skeleton extraction, etc.), curve reconstruction based on noise data …
image edge smoothing, skeleton extraction, etc.), curve reconstruction based on noise data …
Revisiting the Effectiveness of 3D Object Recognition Benchmarks
H Song, S Lee - IEEE Access, 2023 - ieeexplore.ieee.org
Recently, 3D computer vision has greatly emerged and become essential topic in both
research and industry applications. Yet large scale 3D benchmark like ImageNet is not …
research and industry applications. Yet large scale 3D benchmark like ImageNet is not …
Semantic Mapping of Incremental 3D Point Clouds Based on Multi-Hop Graph Attention Network
ST Chen, JC Xu, X Yuan… - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
Mapping and Semantic mapping are the important research areas for the autonomous
navigation of mobile robots. However, realising point cloud information extraction in a …
navigation of mobile robots. However, realising point cloud information extraction in a …
Improving Dental Alignment Accuracy with 3D Scanning and Deep Learning Model Optimization
G Kim, S Lee, J Jeong, Y Jin… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
Recent advancements in deep learning for automatic teeth alignment adopt a method that
extracts dental features through 3D scans and predicts teeth positions using quaternions. In …
extracts dental features through 3D scans and predicts teeth positions using quaternions. In …
Practical processing and acceleration of graph neural networks
S Tailor - 2022 - repository.cam.ac.uk
We have witnessed a dramatic surge in interest in Machine Learning (ML) in the past
decade. Deep neural networks have achieved, or surpassed, human-level on diverse tasks …
decade. Deep neural networks have achieved, or surpassed, human-level on diverse tasks …