2021
DOI: 10.48550/arxiv.2111.14067
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds

Abstract: Fine-grained geometry, captured by aggregation of point features in local regions, is crucial for object recognition and scene understanding in point clouds. Nevertheless, existing preeminent point cloud backbones usually incorporate max/average pooling for local feature aggregation, which largely ignores points' positional distribution, leading to inadequate assembling of fine-grained structures. To mitigate this bottleneck, we present an efficient alternative to max pooling, Position Adaptive Pooling (PAPool… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(1 citation statement)
references
References 47 publications
0
1
0
Order By: Relevance
“…Pooling is a commonly used module in CNNs, which is also known as downsampling [43][44][45]. It is usually used after the convolutional layer to reduce the feature map dimension.…”
Section: Pooling In Cnnmentioning
confidence: 99%
“…Pooling is a commonly used module in CNNs, which is also known as downsampling [43][44][45]. It is usually used after the convolutional layer to reduce the feature map dimension.…”
Section: Pooling In Cnnmentioning
confidence: 99%