arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.14014cs.CVcs.LGeess.IV
收藏

SK-Net:通过端到端空间关键点发现的点云深度学习

SK-Net: Deep Learning on Point Cloud via End-to-end Discovery of Spatial Keypoints

Xiamen University(厦门大学);The Ohio State University(俄亥俄州立大学);Guizhou Normal University(贵州师范大学)

Weikun Wu, Yan Zhang, David Wang, Yunqi Lei

摘要:

自PointNet提出以来,点云上的深度学习一直是3D研究的热点。然而,现有的基于点的方法通常不足以提取的局部特征和空间模式的点云进一步的形状理解。本文提出了一个端到端的框架,SK-Net,共同优化空间关键点的推理与学习的点云的特征表示为一个特定的点云任务。SK-Net的一个关键过程是空间关键点(Skeypoints)的生成。它由两个建议的调节损失和一个任务目标函数联合进行,而不需要了解关键点位置注释和建议。具体来说,我们的关键点对位置一致性不敏感,但对形状有敏锐的认识。SK-Net的另一个关键过程是关键点的局部结构(细节特征)和归一化关键点的局部空间模式(模式特征)的提取。该过程生成一个全面的表示,模式细节(PD)的功能,它包含了点云的局部细节信息,并揭示了其空间模式,通过部分区域重建规范的关键点。因此,我们的网络被提示有效地理解点云的不同区域之间的相关性,并整合点云的上下文信息。在点云任务中,如分类和分割,我们提出的方法比最先进的方法表现更好或相当。我们还提出了一个消融研究,以证明SK-Net的优势。

英文摘要:

Since the PointNet was proposed, deep learning on point cloud has been the concentration of intense 3D research. However, existing point-based methods usually are not adequate to extract the local features and the spatial pattern of a point cloud for further shape understanding. This paper presents an end-to-end framework, SK-Net, to jointly optimize the inference of spatial keypoint with the learning of feature representation of a point cloud for a specific point cloud task. One key process of SK-Net is the generation of spatial keypoints (Skeypoints). It is jointly conducted by two proposed regulating losses and a task objective function without knowledge of Skeypoint location annotations and proposals. Specifically, our Skeypoints are not sensitive to the location consistency but are acutely aware of shape. Another key process of SK-Net is the extraction of the local structure of Skeypoints (detail feature) and the local spatial pattern of normalized Skeypoints (pattern feature). This process generates a comprehensive representation, pattern-detail (PD) feature, which comprises the local detail information of a point cloud and reveals its spatial pattern through the part district reconstruction on normalized Skeypoints. Consequently, our network is prompted to effectively understand the correlation between different regions of a point cloud and integrate contextual information of the point cloud. In point cloud tasks, such as classification and segmentation, our proposed method performs better than or comparable with the state-of-the-art approaches. We also present an ablation study to demonstrate the advantages of SK-Net.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑