arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.08992cs.CV
收藏

基于双反向投影网络的任意点云上采样

Arbitrary point cloud upsampling via Dual Back-Projection Network

Dell(戴尔)

Zhi-Song Liu, Zijia Wang, Zhen Jia

AI总结:

针对3D传感器获取的点云稀疏含噪的问题,提出双反向投影网络DBPnet,通过特征与坐标残差的双向投影实现任意倍率点云上采样,在均匀/非均匀点云上均取得优于基准的重建效果。

摘要:

从3D传感器获取的点云通常是稀疏且含噪的。点云上采样是一种提高点云密度以恢复精细几何信息的方法。本文提出了一种用于点云上采样的双反向投影网络(Dual Back-Projection network,DBPnet)。我们以“上-下-上”的方式构建了用于点云上采样的双反向投影机制,它不仅反向投影特征残差,还反向投影坐标残差,使网络能更好地捕捉特征域和空间域中的点相关性,在均匀和非均匀稀疏点云上均实现了更低的重建误差。本文提出的方法还可推广至任意上采样任务(例如4倍、5.5倍)。实验结果表明,相较于基准方法,该方法取得了最低的点集匹配损失。此外,该方法的成功证明,处理非均匀点云并非一定需要生成式网络。

英文摘要:

Point clouds acquired from 3D sensors are usually sparse and noisy. Point cloud upsampling is an approach to increase the density of the point cloud so that detailed geometric information can be restored. In this paper, we propose a Dual Back-Projection network for point cloud upsampling (DBPnet). A Dual Back-Projection is formulated in an up-down-up manner for point cloud upsampling. It not only back projects feature residues but also coordinates residues so that the network better captures the point correlations in the feature and space domains, achieving lower reconstruction errors on both uniform and non-uniform sparse point clouds. Our proposed method is also generalizable for arbitrary upsampling tasks (e.g. 4x, 5.5x). Experimental results show that the proposed method achieves the lowest point set matching losses with respect to the benchmark. In addition, the success of our approach demonstrates that generative networks are not necessarily needed for non-uniform point clouds.

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。

↑