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 2609.36644cs.CV

OCA:基于ODE驱动的交叉注意力用于图像到点云配准

OCA: ODE-Driven Cross-Attention for Image-to-Point-Cloud Registration

Pei An, Jiaqi Yang, Yulong Wang, Siwen Quan, Liangliang Nan

首次发表
浏览论文内容

中文总结 AI 辅助

针对图像到点云配准中交叉注意力模糊性问题,提出ODE驱动的交叉注意力模块(OCA),通过常微分方程建模特征交互,集成至五个基线,在四个数据集上配准召回率提升最高达15%。

中文摘要 AI 辅助

交叉注意力是基于学习的图像到点云(I2P)配准中的一个关键组件。尽管现有的交叉注意力机制已经取得了显著的进展,但注意力模糊性仍然是一个基本挑战,阻碍了判别性2D-3D对应关系的学习。为了解决这个问题,我们重新审视交叉注意力,并建立常微分方程(ODEs)来建模理想的I2P特征交互。基于这一公式,我们开发了一个ODE驱动的交叉注意力(OCA)模块,通过ODEs细化特征表示和注意力矩阵。在实践中,OCA可以无缝集成到现有的I2P配准框架中。为了验证其有效性,我们将OCA集成到五个最先进的基线中,并在四个公开基准数据集上进行评估。实验结果表明,在标准、微调和零样本设置下,OCA分别将配准召回率提高了最多5%、9%和15%。

英文摘要

Cross-attention is a crucial component in learning-based image-to-point-cloud (I2P) registration. Although existing cross-attention mechanisms have achieved promising progress, attention ambiguity remains a fundamental challenge that hinders the learning of discriminative 2D-3D correspondences. To address this problem, we revisit cross-attention and establish ordinary differential equations (ODEs) to model the ideal I2P feature interaction. Based on this formulation, we develop an ODE-driven cross-attention (OCA) module that refines feature representations and attention matrices through ODEs. In practice, OCA can be seamlessly integrated into existing I2P registration frameworks. To validate its effectiveness, we incorporate OCA into five state-of-the-art baselines and evaluate on four public benchmark datasets. Experimental results demonstrate that OCA improves registration recall by up to 5\%, 9\%, and 15\% under the standard, fine-tuning, and zero-shot settings, respectively.

发表机构

  • Huazhong University of Science and Technology(华中科技大学)
  • Northwestern Polytechnical University(西北工业大学)
  • Huazhong Agricultural University(华中农业大学)
  • Delft University of Technology(代尔夫特理工大学)

机构由 AI 辅助整理,请以论文原文为准。

补充信息

↑