arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.01993cs.CVcs.LG
收藏

一种基于卷积和注意力机制的新型模型用于6D物体姿态估计

A Novel Convolution and Attention Mechanism-based Model for 6D Object Pose Estimation

California Institute of Technology(加州理工学院);University of Michigan(密歇根大学)

Alexander Du, Xiujin Liu

AI总结:

本文提出了一种结合Legendre卷积和注意力机制的新型模型,用于提高单目RGB图像中6D物体姿态估计的性能。

摘要:

本文提出了一种基于图的编码器-解码器框架PoseLecTr,该框架集成了新型Legendre卷积与注意力机制,用于从单目RGB图像中估计六自由度(6-DOF)物体姿态。传统基于学习的方法主要依赖于网格结构的卷积,这可能限制其对图像特征中高阶和长距离依赖关系的建模能力,尤其是在杂乱或遮挡的场景中。PoseLecTr通过从图像特征中构建图表示来解决这一限制,通过图连接显式建模空间关系。所提出的框架包含Legendre卷积层以提高图卷积中的数值稳定性,以及空间注意力和自我注意力蒸馏以增强特征选择。在LINEMOD、Occluded LINEMOD和YCB-VIDEO数据集上进行的实验表明,我们的方法在性能上具有竞争力,并在各种物体和场景复杂度范围内表现出一致的改进。

英文摘要:

This paper proposes PoseLecTr, a graph-based encoder-decoder framework that integrates a novel Legendre convolution with attention mechanisms for six-degree-of-freedom (6-DOF) object pose estimation from monocular RGB images. Conventional learning-based approaches predominantly rely on grid-structured convolutions, which can limit their ability to model higher-order and long-range dependencies among image features, especially in cluttered or occluded scenes. PoseLecTr addresses this limitation by constructing a graph representation from image features, where spatial relationships are explicitly modeled through graph connectivity. The proposed framework incorporates a Legendre convolution layer to improve numerical stability in graph convolution, together with spatial-attention and self-attention distillation to enhance feature selection. Experiments conducted on the LINEMOD, Occluded LINEMOD, and YCB-VIDEO datasets demonstrate that our method achieves competitive performance and shows consistent improvements across a wide range of objects and scene complexities.

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。

↑