[HTML][HTML] Small but mighty: Enhancing 3d point clouds semantic segmentation with u-next framework

Z Zeng, Q Hu, Z Xie, B Li, J Zhou, Y Xu - International Journal of Applied …, 2025 - Elsevier
We investigate the problem of 3D point clouds semantic segmentation. Recently, a large
amount of research work has focused on local feature aggregation. However, the …

3D Shape Segmentation via Attentive Nonuniform Downsampling

Z Shu, X Sun, C Pang, S Xin - IEEE Transactions on Circuits …, 2024 - ieeexplore.ieee.org
The segmentation of 3D shapes is a critical aspect of shape analysis. However, most
existing methods for 3D shape segmentation treat each face of the original mesh model with …

Deep learning-supported machine vision-based hybrid system combining inhomogeneous 2D and 3D data for the identification of surface defects

G Cavaliere, O Lanz, Y Borgianni… - Production & …, 2024 - Taylor & Francis
Machine vision systems for automatic defect detection commonly adopt 2D image-based
systems or 3D laser triangulation systems. 2D and 3D systems present opposite advantages …

Few-shot Point Cloud Semantic Segmentation via Support-Query Feature Interaction

C Zheng, L Liu, Y Meng, X Peng… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Few-shot point cloud semantic segmentation is a challenging problem that aims to use only
a limited number of labeled point clouds to recognize novel samples, significantly reducing …

PointNAT: Large Scale Point Cloud Semantic Segmentation via Neighbor Aggregation with Transformer

Z Zeng, H Qiu, J Zhou, Z Dong… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Given the prominence of 3-D sensors in recent years, 3-D point clouds are worthy to be
further investigated for environment perception and scene understanding. Learning accurate …

Real-Time 3D Visual Perception by Cross-Dimensional Refined Learning

Z Hong, CP Yue - IEEE Transactions on Circuits and Systems …, 2024 - ieeexplore.ieee.org
We introduce a novel learning method that can effectively perceive both the geometry
structure and semantic labels of a 3D scene in real time. Existing real-time 3D scene …

A Semantically Aware Multi-View 3D Reconstruction Method for Urban Applications

R Wei, H Pei, D Wu, C Zeng, X Ai, H Duan - Applied Sciences, 2024 - mdpi.com
The task of 3D reconstruction of urban targets holds pivotal importance for various
applications, including autonomous driving, digital twin technology, and urban planning and …

Real-Scene 3D Urban Elements Modeling for Digital Twin City Construction

Y Li, J Yang, Y Li, X Li, Z Qin… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
This study proposes a novel approach for digital twin modeling of urban elements, aimed at
enhancing the precision and efficiency of large-scale 3D city models. Traditional …