arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.04963cs.CV

VAIR:面向室内场景中低成本、多模态透明表面重建的视觉-声学隐式表示

VAIR: Visuo-Acoustic Implicit Representations for Low-Cost, Multi-Modal Transparent Surface Reconstruction in Indoor Scenes

University of Michigan(密歇根大学)

Advaith V. Sethuraman, Onur Bagoren, Harikrishnan Seetharaman, Dalton Richardson, Joseph Taylor, Katherine A. Skinner

AI总结:

本文提出VAIR方法,通过隐式神经表示融合视觉与声学传感,利用生成式潜在优化学习室内场景隐式表示,实现透明表面密集重建,在低成本平台数据集上显著优于现有技术。

摘要:

在室内运行的移动机器人必须准备好应对包含透明表面的具有挑战性的场景。本文提出了一种通过隐式神经表示融合声学和视觉感知模态的新方法,以实现室内场景中透明表面的密集重建。我们提出了一种新颖的模型,利用生成式潜在优化来学习由透明表面组成的室内场景的隐式表示。我们证明了可以查询该隐式表示,以在图像空间中实现体积渲染,或进行具有透明表面预测的3D几何重建(点云或网格)。我们在一个使用定制的、低成本传感平台(配备RGB-D相机和超声波传感器)收集的新数据集上,对我们的方法进行了定性和定量的评估。我们的方法在透明表面重建方面相较于最先进技术表现出显著改进。

英文摘要:

Mobile robots operating indoors must be prepared to navigate challenging scenes that contain transparent surfaces. This paper proposes a novel method for the fusion of acoustic and visual sensing modalities through implicit neural representations to enable dense reconstruction of transparent surfaces in indoor scenes. We propose a novel model that leverages generative latent optimization to learn an implicit representation of indoor scenes consisting of transparent surfaces. We demonstrate that we can query the implicit representation to enable volumetric rendering in image space or 3D geometry reconstruction (point clouds or mesh) with transparent surface prediction. We evaluate our method's effectiveness qualitatively and quantitatively on a new dataset collected using a custom, low-cost sensing platform featuring RGB-D cameras and ultrasonic sensors. Our method exhibits significant improvement over state-of-the-art for transparent surface reconstruction.

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。

↑