Pointcutmix: Regularization strategy for point cloud classification
As 3D point cloud analysis has received increasing attention, the insufficient scale of point
cloud datasets and the weak generalization ability of networks become prominent. In this …
cloud datasets and the weak generalization ability of networks become prominent. In this …
PDConv: Rigid transformation invariant convolution for 3D point clouds
Rigid transformation poses a big challenge for many deep learning models on 3D point
clouds as the point coordinates can be drastically changed. To tackle this issue, we …
clouds as the point coordinates can be drastically changed. To tackle this issue, we …
Individual pig identification using back surface point clouds in 3D vision
H Zhou, Q Li, Q Xie - Sensors, 2023 - mdpi.com
The individual identification of pigs is the basis for precision livestock farming (PLF), which
can provide prerequisites for personalized feeding, disease monitoring, growth condition …
can provide prerequisites for personalized feeding, disease monitoring, growth condition …
Adaptive multi-hypergraph convolutional networks for 3d object classification
L Nong, J Peng, W Zhang, J Lin, H Qiu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
3D object classification is an important task in computer vision. In order to explore the high-
order and multi-modal correlations among 3D data, we propose an adaptive multi …
order and multi-modal correlations among 3D data, we propose an adaptive multi …
Multi-robot raster map fusion without initial relative position
M Wang, M Cong, Y Du, D Liu, X Tian - Robotic Intelligence and …, 2023 - emerald.com
Purpose The purpose of this study is to solve the problem of an unknown initial position in a
multi-robot raster map fusion. The method includes two-dimensional (2D) raster maps and …
multi-robot raster map fusion. The method includes two-dimensional (2D) raster maps and …
Iterative BTreeNet: Unsupervised learning for large and dense 3D point cloud registration
Abstract 3D point cloud registration is a computational process that aligns two 3D point
clouds through transformation. ie finding matching translation and rotation. Existing state-of …
clouds through transformation. ie finding matching translation and rotation. Existing state-of …
SemRegionNet: Region ensemble 3D semantic instance segmentation network with semantic spatial aware discriminative loss
The semantic instance segmentation task on 3D data has made great progress. However,
for unstructured 3D point cloud data, the mining of regional knowledge and explicit …
for unstructured 3D point cloud data, the mining of regional knowledge and explicit …
An improved fused feature residual network for 3D point cloud data
AS Gezawa, C Liu, H Jia, YA Nanehkaran… - Frontiers in …, 2023 - frontiersin.org
Point clouds have evolved into one of the most important data formats for 3D representation.
It is becoming more popular as a result of the increasing affordability of acquisition …
It is becoming more popular as a result of the increasing affordability of acquisition …
EFSCNN: Encoded Feature Sphere Convolution Neural Network for fast non-rigid 3D models classification and retrieval
Y Zhou, Z Dang, H Zhang, X Xu, J Qin, W Li… - Computer Vision and …, 2023 - Elsevier
Traditional methods of classification and retrieval for non-rigid 3D models, such as
topological structure-based methods and spectral analysis-based methods, high rely on …
topological structure-based methods and spectral analysis-based methods, high rely on …
Winding pathway understanding based on angle projections in a field environment
L Wang, H Wei - Applied Intelligence, 2023 - Springer
Scene understanding is a core problem for autonomous navigation. However, its
implementation is frustrated by a variety of unsettled issues, such as understanding winding …
implementation is frustrated by a variety of unsettled issues, such as understanding winding …