Grad-pu: Arbitrary-scale point cloud upsampling via gradient descent with learned distance functions

Y He, D Tang, Y Zhang, X Xue… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Most existing point cloud upsampling methods have roughly three steps: feature extraction,
feature expansion and 3D coordinate prediction. However, they usually suffer from two …

3DCTN: 3D convolution-transformer network for point cloud classification

D Lu, Q Xie, K Gao, L Xu, J Li - IEEE Transactions on Intelligent …, 2022 - ieeexplore.ieee.org
Point cloud classification is a fundamental task in 3D applications. However, it is challenging
to achieve effective feature learning due to the irregularity and unordered nature of point …

Transformers in 3d point clouds: A survey

D Lu, Q Xie, M Wei, K Gao, L Xu, J Li - arXiv preprint arXiv:2205.07417, 2022 - arxiv.org
Transformers have been at the heart of the Natural Language Processing (NLP) and
Computer Vision (CV) revolutions. The significant success in NLP and CV inspired exploring …

Lcpformer: Towards effective 3d point cloud analysis via local context propagation in transformers

Z Huang, Z Zhao, B Li, J Han - IEEE Transactions on Circuits …, 2023 - ieeexplore.ieee.org
Transformer with its underlying attention mechanism and the ability to capture long-range
dependencies makes it become a natural choice for unordered point cloud data. However …

A survey on transformers for point cloud processing: An updated overview

J Zeng, D Wang, P Chen - IEEE Access, 2022 - ieeexplore.ieee.org
In recent years, the popularity of depth sensors and three-dimensional (3D) scanners has
led to the rapid development of 3D point clouds. A transformer is a type of deep neural …

SAT3D: Slot attention transformer for 3D point cloud semantic segmentation

M Ibrahim, N Akhtar, S Anwar… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Semantic segmentation of 3D point cloud is a key task in numerous intelligent transportation
system applications, eg, self-driving vehicles, traffic monitoring. Due to the sparsity and …

AGConv: Adaptive graph convolution on 3D point clouds

M Wei, Z Wei, H Zhou, F Hu, H Si… - … on Pattern Analysis …, 2023 - ieeexplore.ieee.org
Convolution on 3D point clouds is widely researched yet far from perfect in geometric deep
learning. The traditional wisdom of convolution characterises feature correspondences …

Learning continuous implicit field with local distance indicator for arbitrary-scale point cloud upsampling

S Li, J Zhou, B Ma, YS Liu, Z Han - … of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
Point cloud upsampling aims to generate dense and uniformly distributed point sets from a
sparse point cloud, which plays a critical role in 3D computer vision. Previous methods …

The Applications of 3D Input Data and Scalability Element by Transformer Based Methods: A Review

AS Gezawa, C Liu, NUR Junejo, H Chiroma - Archives of Computational …, 2024 - Springer
Outstanding effectiveness of transformers in visual tasks has resulted in its fast growth and
adoption in three dimensions (3D) vision tasks. Vision transformers have shown numerous …

RepKPU: Point Cloud Upsampling with Kernel Point Representation and Deformation

Y Rong, H Zhou, K Xia, C Mei… - Proceedings of the …, 2024 - openaccess.thecvf.com
In this work we present RepKPU an efficient network for point cloud upsampling. We
propose to promote upsampling performance by exploiting better shape representation and …