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 2011.00931cs.CV
收藏

点式Transformer

Point Transformer

Ulm University(乌尔姆大学)

Nico Engel, Vasileios Belagiannis, Klaus Dietmayer

摘要:

在这项工作中,我们提出了点Transformer,一个深度神经网络,直接对无序和非结构化的点集进行操作。我们设计的点Transformer提取本地和全球的特点,并通过引入本地-全球的注意力机制,其目的是捕捉空间点的关系和形状信息的表示。为此,我们提出了SortNet,作为Point Transformer的一部分,它通过基于学习的分数选择点来诱导输入排列不变性。Point Transformer的输出是一个排序且排列不变的特征列表,可以直接纳入常见的计算机视觉应用程序中。我们评估我们的标准分类和部分分割基准的方法,以证明竞争力的结果相比,以前的工作。代码可在https://github.com/engelnico/point-transformer上公开获取

英文摘要:

In this work, we present Point Transformer, a deep neural network that operates directly on unordered and unstructured point sets. We design Point Transformer to extract local and global features and relate both representations by introducing the local-global attention mechanism, which aims to capture spatial point relations and shape information. For that purpose, we propose SortNet, as part of the Point Transformer, which induces input permutation invariance by selecting points based on a learned score. The output of Point Transformer is a sorted and permutation invariant feature list that can directly be incorporated into common computer vision applications. We evaluate our approach on standard classification and part segmentation benchmarks to demonstrate competitive results compared to the prior work. Code is publicly available at: https://github.com/engelnico/point-transformer

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。

↑