Attention mechanisms in computer vision: A survey

MH Guo, TX Xu, JJ Liu, ZN Liu, PT Jiang, TJ Mu… - Computational visual …, 2022 - Springer
Humans can naturally and effectively find salient regions in complex scenes. Motivated by
this observation, attention mechanisms were introduced into computer vision with the aim of …

Unsupervised point cloud representation learning with deep neural networks: A survey

A **ao, J Huang, D Guan, X Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Point cloud data have been widely explored due to its superior accuracy and robustness
under various adverse situations. Meanwhile, deep neural networks (DNNs) have achieved …

Snowflakenet: Point cloud completion by snowflake point deconvolution with skip-transformer

P **ang, X Wen, YS Liu, YP Cao… - Proceedings of the …, 2021 - openaccess.thecvf.com
Point cloud completion aims to predict a complete shape in high accuracy from its partial
observation. However, previous methods usually suffered from discrete nature of point cloud …

Pmp-net: Point cloud completion by learning multi-step point moving paths

X Wen, P **ang, Z Han, YP Cao… - Proceedings of the …, 2021 - openaccess.thecvf.com
The task of point cloud completion aims to predict the missing part for an incomplete 3D
shape. A widely used strategy is to generate a complete point cloud from the incomplete …

Pmp-net++: Point cloud completion by transformer-enhanced multi-step point moving paths

X Wen, P **ang, Z Han, YP Cao, P Wan… - … on Pattern Analysis …, 2022 - ieeexplore.ieee.org
Point cloud completion concerns to predict missing part for incomplete 3D shapes. A
common strategy is to generate complete shape according to incomplete input. However …

Point cloud completion by skip-attention network with hierarchical folding

X Wen, T Li, Z Han, YS Liu - … of the IEEE/CVF conference on …, 2020 - openaccess.thecvf.com
Point cloud completion aims to infer the complete geometries for missing regions of 3D
objects from incomplete ones. Previous methods usually predict the complete point cloud …

Learning a more continuous zero level set in unsigned distance fields through level set projection

J Zhou, B Ma, S Li, YS Liu… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Latest methods represent shapes with open surfaces using unsigned distance functions
(UDFs). They train neural networks to learn UDFs and reconstruct surfaces with the …

Geometric back-projection network for point cloud classification

S Qiu, S Anwar, N Barnes - IEEE Transactions on Multimedia, 2021 - ieeexplore.ieee.org
As the basic task of point cloud analysis, classification is fundamental but always
challenging. To address some unsolved problems of existing methods, we propose a …

M3detr: Multi-representation, multi-scale, mutual-relation 3d object detection with transformers

T Guan, J Wang, S Lan, R Chandra… - Proceedings of the …, 2022 - openaccess.thecvf.com
We present a novel architecture for 3D object detection, M3DETR, which combines different
point cloud representations (raw, voxels, bird-eye view) with different feature scales based …

Cycle4completion: Unpaired point cloud completion using cycle transformation with missing region coding

X Wen, Z Han, YP Cao, P Wan… - Proceedings of the …, 2021 - openaccess.thecvf.com
In this paper, we present a novel unpaired point cloud completion network, named
Cycle4Completion, to infer the complete geometries from a partial 3D object. Previous …