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 1508.04546cs.CV
收藏

RGB-D图像中6D位姿估计的学习合成分析

Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Images

TU Dresden(德累斯顿工业大学)

Alexander Krull, Eric Brachmann, Frank Michel, Michael Ying Yang, Stefan Gumhold, Carsten Rother

摘要:

综合分析已经成为计算机视觉中许多任务的成功方法,例如RGB-D图像中对象的6D姿态估计,这是这项工作的主题。这个想法是将观察结果与前向过程的输出进行比较,例如特定姿势的感兴趣对象的渲染图像。由于遮挡或复杂的传感器噪声,可能难以以有意义的方式执行该比较。我们提出了一种方法,“学会比较”,同时考虑到这些困难。这是通过用卷积神经网络(CNN)描述特定对象姿态的后验密度来完成的,该卷积神经网络比较观察到的图像和渲染的图像。该网络是用最大似然范式训练的。我们凭经验观察到,CNN并不专门针对特定对象的几何形状或外观,它可以用于形状和外观截然不同的对象,以及不同的背景。与最先进的技术相比,我们在两个不同的数据集上展示了显着的改进,其中包括总共11个对象,杂乱的背景和严重的遮挡。

英文摘要:

Analysis-by-synthesis has been a successful approach for many tasks in computer vision, such as 6D pose estimation of an object in an RGB-D image which is the topic of this work. The idea is to compare the observation with the output of a forward process, such as a rendered image of the object of interest in a particular pose. Due to occlusion or complicated sensor noise, it can be difficult to perform this comparison in a meaningful way. We propose an approach that "learns to compare", while taking these difficulties into account. This is done by describing the posterior density of a particular object pose with a convolutional neural network (CNN) that compares an observed and rendered image. The network is trained with the maximum likelihood paradigm. We observe empirically that the CNN does not specialize to the geometry or appearance of specific objects, and it can be used with objects of vastly different shapes and appearances, and in different backgrounds. Compared to state-of-the-art, we demonstrate a significant improvement on two different datasets which include a total of eleven objects, cluttered background, and heavy occlusion.

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。

↑