ARTÍCULO
TITULO

Point Cloud Convolution Network Based on Spatial Location Correspondence

Jiabin Xv    
Fei Deng and Haibing Liu    

Resumen

The study of convolutional neural networks for 3D point clouds is becoming increasingly popular, and the difficulty lies mainly in the disorder and irregularity of point clouds. At present, it is straightforward to propose a convolution operation and perform experimental validation. Although good results are achieved, the principles behind them are not explained?i.e., why this can solve the disorder and irregularity of point clouds?and it is difficult for the researchers to design a point cloud convolution network suitable for their needs. For this phenomenon, we propose a point convolution network framework based on spatial location correspondence. Following the correspondence principle can guide us in designing convolution networks adapted to our needs. We analyzed the intrinsic mathematical nature of the convolution operation, and we argue that the convolution operation remains the same when the spatial location correspondence between the convolution kernel points and the convolution range elements remains unchanged. Guided by this principle, we formulated a general point convolution framework based on spatial location correspondence, which explains how to handle a disordered point cloud. Moreover, we discuss different kinds of correspondence based on spatial location, including M-to-M, M-to-N, and M-to-1 relationships, etc., which explain how to handle the irregularity of point clouds. Finally, we give the example of a point convolution network whose convolution kernel points are generated based on the sample?s covariance matrix distribution according to our framework. Our convolution operation can be applied to various point cloud processing networks. We demonstrated the effectiveness of our framework for point cloud classification and semantic segmentation tasks, achieving competitive results with state-of-the-art networks.

 Artículos similares

       
 
Abderrazzaq Kharroubi, Zouhair Ballouch, Rafika Hajji, Anass Yarroudh and Roland Billen    
Railway scene understanding is crucial for various applications, including autonomous trains, digital twining, and infrastructure change monitoring. However, the development of the latter is constrained by the lack of annotated datasets and limitations o... ver más
Revista: Infrastructures

 
Yee Sye Lee, Ali Rashidi, Amin Talei and Daniel Kong    
In recent years, mixed reality (MR) technology has gained popularity in construction management due to its real-time visualisation capability to facilitate on-site decision-making tasks. The semantic segmentation of building components provides an attrac... ver más
Revista: Buildings

 
Mikael Sabuhi, Petr Musilek and Cor-Paul Bezemer    
As the number of machine learning applications increases, growing concerns about data privacy expose the limitations of traditional cloud-based machine learning methods that rely on centralized data collection and processing. Federated learning emerges a... ver más
Revista: Future Internet

 
Mizuki Asano, Takumi Miyoshi and Taku Yamazaki    
Smart home environments, which consist of various Internet of Things (IoT) devices to support and improve our daily lives, are expected to be widely adopted in the near future. Owing to a lack of awareness regarding the risks associated with IoT devices ... ver más
Revista: Future Internet

 
Shuo Shi, Xingtao Tang, Bowen Chen, Biwu Chen, Qian Xu, Sifu Bi and Wei Gong    
Lidar can effectively obtain three-dimensional information on ground objects. In recent years, lidar has developed rapidly from single-wavelength to multispectral hyperspectral imaging. The multispectral airborne lidar Optech Titan is the first commercia... ver más