arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.00678cs.CV
收藏

基于Transformers的无群组3D目标检测

Group-Free 3D Object Detection via Transformers

University of Science and Technology of China(中国科学技术大学);Microsoft Research Asia(微软亚洲研究院)

Ze Liu, Zheng Zhang, Yue Cao, Han Hu, Xin Tong

摘要:

近年来,直接从三维点云中检测三维物体受到越来越多的关注。为了从不规则的点云中提取对象表示,现有的方法通常采取点分组步骤来将点分配给对象候选者,以便可以使用PointNet类网络来从分组的点中获得对象特征。然而,不准确的点分配所造成的手工编制的分组方案降低了三维目标检测的性能。在本文中,我们提出了一种简单而有效的方法,直接检测三维物体的三维点云。我们的方法不是将局部点分组到每个对象候选者,而是在Transformers \cite{vaswani2017attention}中的注意力机制的帮助下,从点云中的所有点计算对象的特征,其中每个点的贡献在网络训练中自动学习。该方法采用改进的注意力叠加方法,融合了不同阶段的目标特征,得到了更准确的目标检测结果。所提出的方法在两个广泛使用的基准测试ScanNet V2和SUN RGB-D上实现了最先进的3D目标检测性能。代码和模型可在\url{https://github.com/zeliu98/Group-Free-3D}上公开获取

英文摘要:

Recently, directly detecting 3D objects from 3D point clouds has received increasing attention. To extract object representation from an irregular point cloud, existing methods usually take a point grouping step to assign the points to an object candidate so that a PointNet-like network could be used to derive object features from the grouped points. However, the inaccurate point assignments caused by the hand-crafted grouping scheme decrease the performance of 3D object detection. In this paper, we present a simple yet effective method for directly detecting 3D objects from the 3D point cloud. Instead of grouping local points to each object candidate, our method computes the feature of an object from all the points in the point cloud with the help of an attention mechanism in the Transformers \cite{vaswani2017attention}, where the contribution of each point is automatically learned in the network training. With an improved attention stacking scheme, our method fuses object features in different stages and generates more accurate object detection results. With few bells and whistles, the proposed method achieves state-of-the-art 3D object detection performance on two widely used benchmarks, ScanNet V2 and SUN RGB-D. The code and models are publicly available at \url{https://github.com/zeliu98/Group-Free-3D}

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。

↑