arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.07203cs.CVcs.RO
收藏

单视图RGB图像的类别级三维非刚性配准

Category-Level 3D Non-Rigid Registration from Single-View RGB Images

University of Bonn(波恩大学)

Diego Rodriguez, Florian Huber, Sven Behnke

摘要:

在本文中,我们提出了一种新的方法来解决三维非刚性配准问题,从RGB图像使用卷积神经网络(CNN)。我们的目标是找到一个变形场(通常用于在实例之间传递知识,例如,掌握技能),其将给定的3D规范模型扭曲成由单视图RGB图像观察到的新颖实例。这是通过训练CNN来完成的,该CNN为规范模型的可见部分推断变形场,并且通过采用学习的形状(潜在)空间来推断被遮挡部分的变形。作为配准的结果,重建所观察的模型。因为我们的方法不需要深度信息,所以它可以配准通常难以用RGB-D传感器感知的物体,例如具有透明或闪亮表面的物体。即使没有深度数据,我们的方法优于相干点漂移(CPD)注册方法的评估对象类别。

英文摘要:

In this paper, we propose a novel approach to solve the 3D non-rigid registration problem from RGB images using Convolutional Neural Networks (CNNs). Our objective is to find a deformation field (typically used for transferring knowledge between instances, e.g., grasping skills) that warps a given 3D canonical model into a novel instance observed by a single-view RGB image. This is done by training a CNN that infers a deformation field for the visible parts of the canonical model and by employing a learned shape (latent) space for inferring the deformations of the occluded parts. As result of the registration, the observed model is reconstructed. Because our method does not need depth information, it can register objects that are typically hard to perceive with RGB-D sensors, e.g. with transparent or shiny surfaces. Even without depth data, our approach outperforms the Coherent Point Drift (CPD) registration method for the evaluated object categories.

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。

↑