Implicit Guidance and Explicit Representation of Semantic Information in Points Cloud: A Survey

J Tang, Y Zhao, S Sun, Y Cai - arxiv preprint arxiv:2501.05473, 2025‏ - arxiv.org
Point clouds, a prominent method of 3D representation, are extensively utilized across
industries such as autonomous driving, surveying, electricity, architecture, and gaming, and …

Curriculumformer: Taming Curriculum Pre-Training for Enhanced 3-D Point Cloud Understanding

B Fei, T Luo, W Yang, L Liu, R Zhang… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Learning universal representations of 3-D point clouds is essential for reducing the need for
manual annotation of large-scale and irregular point cloud datasets. The current modus …

[HTML][HTML] Multi-Scale Classification and Contrastive Regularization: Weakly Supervised Large-Scale 3D Point Cloud Semantic Segmentation

J Wang, J He, Y Liu, C Chen, M Zhang, H Tan - Remote Sensing, 2024‏ - mdpi.com
With the proliferation of large-scale 3D point cloud datasets, the high cost of per-point
annotation has spurred the development of weakly supervised semantic segmentation …

Unsupervised deep learning for semantic segmentation of multispectral LiDAR forest point clouds

L Ruoppa, O Oinonen, J Taher, M Lehtomäki… - arxiv preprint arxiv …, 2025‏ - arxiv.org
Point clouds captured with laser scanning systems from forest environments can be utilized
in a wide variety of applications within forestry and plant ecology, such as the estimation of …

Aligning Instance-Semantic Sparse Representation towards Unsupervised Object Segmentation and Shape Abstraction with Repeatable Primitives

J Li, H Wang, J Tan, Z Ou, J Yuan - IEEE Transactions on …, 2025‏ - ieeexplore.ieee.org
Understanding 3D object shapes necessitates shape representation by object parts
abstracted from results of instance and semantic segmentation. Promising shape …

Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation

Z Pan, W Gao, S Liu, G Li - arxiv preprint arxiv:2410.08091, 2024‏ - arxiv.org
Despite alleviating the dependence on dense annotations inherent to fully supervised
methods, weakly supervised point cloud semantic segmentation suffers from inadequate …

Unsupervised semantic segmentation of urban high-density multispectral point clouds

O Oinonen, L Ruoppa, J Taher, M Lehtomäki… - arxiv preprint arxiv …, 2024‏ - arxiv.org
The availability of highly accurate urban airborne laser scanning (ALS) data will increase
rapidly in the future, especially as acquisition costs decrease, for example through the use of …

[معلومات الإصدار][C] Máster Universitario en Inteligencia Artificial

CG García, G Romero