Saved in:
Bibliographic Details
Main Authors: Du, Alexander, Liu, Xiujin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2501.01993
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911357138370560
author Du, Alexander
Liu, Xiujin
author_facet Du, Alexander
Liu, Xiujin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_01993
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Novel Convolution and Attention Mechanism-based Model for 6D Object Pose Estimation
Du, Alexander
Liu, Xiujin
Computer Vision and Pattern Recognition
Machine Learning
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.
title A Novel Convolution and Attention Mechanism-based Model for 6D Object Pose Estimation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2501.01993