arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2505.04485cs.CV
收藏

FA-KPConv:通过帧平均将欧几里得对称性引入KPConv

FA-KPConv: Introducing Euclidean Symmetries to KPConv via Frame Averaging

Robert Bosch GmbH - ADAS Systems, Software & Services(博世集团-ADAS系统、软件与服务);University of Lübeck - Institute for Signal Processing(吕贝克大学-信号处理研究所)

Ali Alawieh, Alexandru P. Condurache

AI总结:

本文提出FA-KPConv,通过帧平均将精确的欧几里得不变性与等变性引入KPConv点云网络,在不增加可学习参数的前提下提升分类与配准在数据稀缺和随机旋转等困难场景下的性能。

摘要:

我们提出帧平均核点卷积(FA-KPConv),这是一种构建在著名KPConv之上的神经网络架构,KPConv是3D点云分析中被广泛采用的主干网络。尽管许多常见任务需要对欧几里得变换具有不变性和/或等变性,但基于KPConv的网络只有在大型数据集上训练或进行大量数据增强时才能近似实现这些性质。利用帧平均(Frame Averaging),我们能够灵活定制由KPConv层构建的点云神经网络,使其对输入点云的平移、旋转和/或反射具有精确的不变性和/或等变性。通过简单地包裹现有的基于KPConv的网络,FA-KPConv将几何先验知识嵌入其中,同时保持可学习参数的数量不变,并且不损害任何输入信息。我们展示了这种引入的偏置在点云分类和点云配准中的优势,尤其是在训练数据稀缺或测试数据随机旋转等具有挑战性的情况下。

英文摘要:

We present Frame-Averaging Kernel-Point Convolution (FA-KPConv), a neural network architecture built on top of the well-known KPConv, a widely adopted backbone for 3D point cloud analysis. Even though invariance and/or equivariance to Euclidean transformations are required for many common tasks, KPConv-based networks can only approximately achieve such properties when training on large datasets or with significant data augmentations. Using Frame Averaging, we allow to flexibly customize point cloud neural networks built with KPConv layers, by making them exactly invariant and/or equivariant to translations, rotations and/or reflections of the input point clouds. By simply wrapping around an existing KPConv-based network, FA-KPConv embeds geometrical prior knowledge into it while preserving the number of learnable parameters and not compromising any input information. We showcase the benefit of such an introduced bias for point cloud classification and point cloud registration, especially in challenging cases such as scarce training data or randomly rotated test data.

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。

↑