arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1802.08275cs.CVcs.GR
收藏

SPLATNet:用于点云处理的稀疏格网

SPLATNet: Sparse Lattice Networks for Point Cloud Processing

UMass Amherst(马萨诸塞大学阿默斯特分校);NVIDIA(英伟达);UC Merced(加州大学默塞德分校)

Hang Su, Varun Jampani, Deqing Sun, Subhransu Maji, Evangelos Kalogerakis, Ming-Hsuan Yang, Jan Kautz

摘要:

我们提出了一个网络架构处理点云,直接操作的一组点表示为一个稀疏的样本在一个高维的晶格。在这个网格上简单地应用卷积,随着网格大小的增加,在内存和计算成本方面的伸缩性都很差。相反,我们的网络使用稀疏双边卷积层作为构建块。这些层通过使用索引结构来仅在晶格的占用部分上应用卷积来保持效率,并且允许晶格结构的灵活规范,从而实现分层和空间感知特征学习以及联合2D-3D推理。基于点和基于图像的表示都可以很容易地合并到具有这些层的网络中,并且可以以端到端的方式训练所得到的模型。我们目前的3D分割任务的结果,我们的方法优于现有的最先进的技术。

英文摘要:

We present a network architecture for processing point clouds that directly operates on a collection of points represented as a sparse set of samples in a high-dimensional lattice. Naively applying convolutions on this lattice scales poorly, both in terms of memory and computational cost, as the size of the lattice increases. Instead, our network uses sparse bilateral convolutional layers as building blocks. These layers maintain efficiency by using indexing structures to apply convolutions only on occupied parts of the lattice, and allow flexible specifications of the lattice structure enabling hierarchical and spatially-aware feature learning, as well as joint 2D-3D reasoning. Both point-based and image-based representations can be easily incorporated in a network with such layers and the resulting model can be trained in an end-to-end manner. We present results on 3D segmentation tasks where our approach outperforms existing state-of-the-art techniques.

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。

↑