Attention-based point cloud edge sampling

C Wu, J Zheng, J Pfrommer… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Point cloud sampling is a less explored research topic for this data representation. The most
commonly used sampling methods are still classical random sampling and farthest point …

Lightn: Light-weight transformer network for performance-overhead tradeoff in point cloud downsampling

X Wang, Y **, Y Cen, T Wang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Downsampling is a crucial task for processing large scale and/or dense point clouds with
limited resources. Owing to the development of deep learning, approaches of task-oriented …

Hierarchical edge aware learning for 3d point cloud

L Li - Computer Graphics International Conference, 2023 - Springer
This paper proposes an innovative approach to H ierarchical E dge A ware 3D Point Cloud
Learning (HEA-Net) that seeks to address the challenges of noise in point cloud data, and …

APSNet: Attention based point cloud sampling

Y Ye, X Yang, S Ji - arxiv preprint arxiv:2210.05638, 2022 - arxiv.org
Processing large point clouds is a challenging task. Therefore, the data is often
downsampled to a smaller size such that it can be stored, transmitted and processed more …

Edge aware learning for 3d point cloud

L Li - arxiv preprint arxiv:2309.13472, 2023 - arxiv.org
This paper proposes an innovative approach to Hierarchical Edge Aware 3D Point Cloud
Learning (HEA-Net) that seeks to address the challenges of noise in point cloud data, and …

PIF-Net: A Deep Point-Image Fusion Network for Multi-Modality Semantic Segmentation of Very High Resolution Imagery and Aerial Point Cloud

Z Guo, R Xu, CC Feng, Z Zeng - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Semantic segmentation is of great significance in many applications. However, automating
such a task on single-modality data is challenging in the field of remote sensing due to …

Compressed point cloud classification with point-based edge sampling

Z Luo, W Jia, S Perry - EURASIP Journal on Image and Video Processing, 2024 - Springer
Abstract 3D point cloud data, as an immersive detailed data source, has been increasingly
used in numerous applications. To deal with the computational and storage challenges of …

CAS-Net: Cascade Attention-Based Sampling Neural Network for Point Cloud Simplification

C Chen, H Yuan, H Liu, J Hou… - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
Point cloud sampling can reduce storage requirements and computation costs for various
vision tasks. Traditional sampling methods, such as farthest point sampling, are not geared …

AS-PD: An Arbitrary-Size Downsampling Framework for Point Clouds

P Zhang, R **e, J Sun, W Li, Z Su - arxiv preprint arxiv:2211.01110, 2022 - arxiv.org
Point cloud downsampling is a crucial pre-processing operation to downsample points in
order to unify data size and reduce computational cost, to name a few. Recent research on …

Learnable Point Cloud Sampling Considering Seed Point for Neural Surface Reconstruction

K Matsuzaki, K Nonaka - IEEE Access, 2024 - ieeexplore.ieee.org
Reconstruction of surfaces from point clouds is essential in numerous practical applications.
An approach in which neural fields are trained as surface representations from point clouds …