GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud

Chen, Can; Fragonara, Luca Zanotti; Tsourdos, Antonios

doi:10.48550/arxiv.1905.08705

Cited by 31 publications

(42 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Refs. [52][53][54] intuitively leverage attention-based graph structures to capture the fine-grained features of 3D points for point cloud classification and segmentation. Ref.…”

Section: Related Workmentioning

confidence: 99%

ARM3D: Attention-based relation module for indoor 3D object detection

et al. 2022

View full text Add to dashboard Cite

Relation contexts have been proved to be useful for many challenging vision tasks. In the field of 3D object detection, previous methods have been taking the advantage of context encoding, graph embedding, or explicit relation reasoning to extract relation contexts. However, there exist inevitably redundant relation contexts due to noisy or low-quality proposals. In fact, invalid relation contexts usually indicate underlying scene misunderstanding and ambiguity, which may, on the contrary, reduce the performance in complex scenes. Inspired by recent attention mechanism like Transformer, we propose a novel 3D attention-based relation module (ARM3D). It encompasses object-aware relation reasoning to extract pair-wise relation contexts among qualified proposals and an attention module to distribute attention weights towards different relation contexts. In this way, ARM3D can take full advantage of the useful relation contexts and filter those less relevant or even confusing contexts, which mitigates the ambiguity in detection. We have evaluated the effectiveness of ARM3D by plugging it into several state-of-the-art 3D object detectors and showing more accurate and robust detection results. Extensive experiments show the capability and generalization of ARM3D on 3D object detection. Our source code is available at https://github.com/lanlan96/ARM3D.

show abstract

“…Refs. [52][53][54] intuitively leverage attention-based graph structures to capture the fine-grained features of 3D points for point cloud classification and segmentation. Ref.…”

Section: Related Workmentioning

confidence: 99%

ARM3D: Attention-based relation module for indoor 3D object detection

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The local information is then used to create high level features for each point that retains the information of the local neighborhood. ABCNet, on the other hand, uses the local information to define an attention mechanism, first introduced in [18] and applied in [19]. A similar concept of attention mechanisms are defined for PCT, where a self-attention layer is used to provide the relationship importance between all particles in the set.…”

Section: Related Workmentioning

confidence: 99%

Point Cloud Transformers applied to Collider Physics

Mikuni,

Canelli

2021

Preprint

View full text Add to dashboard Cite

Methods for processing point cloud information have seen a great success in collider physics applications. One recent breakthrough in machine learning is the usage of Transformer networks to learn semantic relationships between sequences in language processing. In this work, we apply a modified Transformer network called Point Cloud Transformer as a method to incorporate the advantages of the Transformer architecture to an unordered set of particles resulting from collision events. To compare the performance with other strategies, we study jet-tagging applications for highly-boosted particles.

show abstract

“…It captures the geometric relationship between points by constructing point and its nearest neighbor points into a graph, but it ignores vector direction between adjacent points, and eventually loses a part of local geometric information. GAPNet [8] introduces the graph attention mechanism and introduces self-attention and neighborhood attention mechanisms. It extracts the fine-grained local features of point-cloud in a manner of attention.…”

Section: B Models Based On Point-cloud Datamentioning

confidence: 99%

“…In recent years, graph-based attention mechanism has been widely used in the field of 3D point-cloud sensing field. [8] proposed GAPNet (Graph Attention based Point Neural Network) to learn local geometric representations that are helpful towards contextual learning by embedding graph attention mechanism within stacked MLP (Multi-Layer-Perceptron) layers.…”

Section: Introductionmentioning

confidence: 99%

MANet: Multimodal Attention Network based Point-View Fusion for 3D Shape Recognition

Zhao

Jiao

et al. 2021

2020 25th International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

3D shape recognition has attracted more and more attention as a task of 3D vision research. The proliferation of 3D data encourages various deep learning methods based on 3D data. Now there have been many deep learning models based on pointcloud data or multi-view data alone. However, in the era of big data, integrating data of two different modals to obtain a unified 3D shape descriptor is bound to improve the recognition accuracy. Therefore, this paper proposes a fusion network based on multimodal attention mechanism for 3D shape recognition. Considering the limitations of multi-view data, we introduce a soft attention scheme, which can use the global point-cloud features to filter the multi-view features, and then realize the effective fusion of the two features. More specifically, we obtain the enhanced multi-view features by mining the contribution of each multi-view image to the overall shape recognition, and then fuse the point-cloud features and the enhanced multi-view features to obtain a more discriminative 3D shape descriptor. We have performed relevant experiments on the ModelNet40 dataset, and experimental results verify the effectiveness of our method.

show abstract

GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud

Cited by 31 publications

References 0 publications

ARM3D: Attention-based relation module for indoor 3D object detection

ARM3D: Attention-based relation module for indoor 3D object detection

Point Cloud Transformers applied to Collider Physics

MANet: Multimodal Attention Network based Point-View Fusion for 3D Shape Recognition

Contact Info

Product

Resources

About