arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.00485cs.CVcs.GR
收藏

SymmetryNet:学习从单视图RGB-D图像预测三维物体的反射对称性和旋转对称性

SymmetryNet: Learning to Predict Reflectional and Rotational Symmetries of 3D Shapes from Single-View RGB-D Images

National University of Defense Technology(国防科技大学);Princeton University(普林斯顿大学)

Yifei Shi, Junwen Huang, Hongjia Zhang, Xin Xu, Szymon Rusinkiewicz, Kai Xu

摘要:

我们研究了单视图RGB-D图像中3D形状的对称性检测问题,其中严重缺失的数据使得几何检测方法不可行。我们提出了一个端到端的深度神经网络,它能够预测输入RGB-D图像中存在的3D对象的反射和旋转对称性。然而,直接训练用于对称性预测的深度模型可能很快就会遇到过拟合问题。我们采用多任务学习方法。除了对称轴预测之外,我们的网络还被训练来预测对称对应。特别是,给定RGB-D图像中存在的3D点,我们的网络为每个3D点输出对应于特定预测对称性的对称对应物。此外,我们的网络能够检测给定形状的多种不同类型的对称性。我们还提供了一个基于单视图RGB-D图像的3D对称性检测基准。在基准测试中的广泛评估表明,我们的方法具有很强的泛化能力,在对称轴预测和对应估计的高精度方面。特别是,我们的方法是强大的,在处理看不见的对象实例的形状变化大,多对称组成,以及新的对象类别。

英文摘要:

We study the problem of symmetry detection of 3D shapes from single-view RGB-D images, where severely missing data renders geometric detection approach infeasible. We propose an end-to-end deep neural network which is able to predict both reflectional and rotational symmetries of 3D objects present in the input RGB-D image. Directly training a deep model for symmetry prediction, however, can quickly run into the issue of overfitting. We adopt a multi-task learning approach. Aside from symmetry axis prediction, our network is also trained to predict symmetry correspondences. In particular, given the 3D points present in the RGB-D image, our network outputs for each 3D point its symmetric counterpart corresponding to a specific predicted symmetry. In addition, our network is able to detect for a given shape multiple symmetries of different types. We also contribute a benchmark of 3D symmetry detection based on single-view RGB-D images. Extensive evaluation on the benchmark demonstrates the strong generalization ability of our method, in terms of high accuracy of both symmetry axis prediction and counterpart estimation. In particular, our method is robust in handling unseen object instances with large variation in shape, multi-symmetry composition, as well as novel 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。

↑