Pointwise Convolutional Neural Networks

Hua, Binh-Son; Tran, Minh-Khoi; Yeung, Sai-Kit

doi:10.48550/arxiv.1712.05245

Cited by 5 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, they projected the spherical neighbourhood onto the ring and then constructed an orthogonal tangent to the point from the normal vector at the centre of each ring, and for the same ring, all the point clouds above the ring were projected onto this tangent. Hua et al (2018) designed a point convolution structure centred on each point. Thomas et al (2019) determined a spherical neighbourhood and identified several kernel points within the neighbourhood, which will carry a weight matrix.…”

Section: Point-based Methodsmentioning

confidence: 99%

Indoor point cloud semantic segmentation based on direction perception and hole sampling

Chen,

Li,

Zhao

et al. 2024

The Photogrammetric Record

View full text Add to dashboard Cite

Most existing point cloud segmentation methods ignore directional information when extracting neighbourhood features. Those methods are ineffective in extracting point cloud neighbourhood features because the point cloud data is not uniformly distributed and is restricted by the size of the convolution kernel. Therefore, we take into account both multiple directions and hole sampling (MDHS). First, we execute spherically sparse sampling with directional encoding in the surrounding domain for every point inside the data to increase the local perceptual field. The data input is the basic geometric features. We use the graph convolutional neural network to conduct the maximisation of point cloud characteristics in a local neighbourhood. Then the more representative local point features are automatically weighted and fused by an attention pooling layer. Finally, spatial attention is added to increase the connection between remote points, and then the segmentation accuracy is improved. Experimental results show that the OA and mIoU are 1.3% and 4.0% higher than the method PointWeb and 0.6% and 0.7% higher than the baseline method RandLA‐Net. For the indoor point cloud semantic segmentation, the segmentation effect of the proposed network is superior to other methods.

show abstract

Section: Point-based Methodsmentioning

confidence: 99%

Indoor point cloud semantic segmentation based on direction perception and hole sampling

Chen,

Li,

Zhao

et al. 2024

The Photogrammetric Record

View full text Add to dashboard Cite

show abstract

“…The latter was tackled by using supervised, unsupervised and autoencoder methods [96][97][98]. Finally, additional methods have been developed focusing on capturing local structures and providing richer representations through sampling, grouping, and mapping functions [98,99].…”

Section: A Brief Review Of Dl-based Point Cloud Processing and Corres...mentioning

confidence: 99%

Deep learning based computer vision under the prism of 3D point clouds: a systematic review

Tychola,

Vrochidou,

Papakostas

2024

Vis Comput

View full text Add to dashboard Cite

Point clouds consist of 3D data points and are among the most considerable data formats for 3D representations. Their popularity is due to their broad application areas, such as robotics and autonomous driving, and their employment in basic 3D vision tasks such as segmentation, classification, and detection. However, processing point clouds is challenging compared to other visual forms such as images, mainly due to their unstructured nature. Deep learning (DL) has been established as a powerful tool for data processing, reporting remarkable performance enhancements compared to traditional methods for all basic 2D vision tasks. However new challenges are emerging when it comes to processing unstructured 3D point clouds. This work aims to guide future research by providing a systematic review of DL on 3D point clouds, holistically covering all 3D vision tasks. 3D technologies of point cloud formation are reviewed and compared to each other. The application of DL methods for point cloud processing is discussed, and state-of-the-art models’ performances are compared focusing on challenges and solutions. Moreover, in this work the most popular 3D point cloud benchmark datasets are summarized based on their task-oriented applications, aiming to highlight existing constraints and to comparatively evaluate them. Future research directions and upcoming trends are also highlighted.

show abstract

“…Thus, the NN learns how to best approximate spatial derivatives specific to the underlying data. Subsequently, the inputs of N T are combined with point-wise CNNs [334] in [332] or a symbolic network in [333]. Both yield an interpretable operator from which the analytical expression can be extracted.…”

Section: Inverse Problemsmentioning

confidence: 99%

Deep learning in computational mechanics: a review

Herrmann,

Kollmannsberger

2024

Comput Mech

View full text Add to dashboard Cite

The rapid growth of deep learning research, including within the field of computational mechanics, has resulted in an extensive and diverse body of literature. To help researchers identify key concepts and promising methodologies within this field, we provide an overview of deep learning in deterministic computational mechanics. Five main categories are identified and explored: simulation substitution, simulation enhancement, discretizations as neural networks, generative approaches, and deep reinforcement learning. This review focuses on deep learning methods rather than applications for computational mechanics, thereby enabling researchers to explore this field more effectively. As such, the review is not necessarily aimed at researchers with extensive knowledge of deep learning—instead, the primary audience is researchers on the verge of entering this field or those attempting to gain an overview of deep learning in computational mechanics. The discussed concepts are, therefore, explained as simple as possible.

show abstract

Pointwise Convolutional Neural Networks

Cited by 5 publications

References 31 publications

Indoor point cloud semantic segmentation based on direction perception and hole sampling

Indoor point cloud semantic segmentation based on direction perception and hole sampling

Deep learning based computer vision under the prism of 3D point clouds: a systematic review

Deep learning in computational mechanics: a review

Contact Info

Product

Resources

About