arXiv 2308.099162023-08-19cs.CV

VI-Net：通过在球面表示上学习解耦旋转提升类别级6D物体姿态估计

VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations

South China University of Technology（华南理工大学）；DexForce Technology Co. Ltd.（德擎科技有限公司）；Hong Kong Polytechnic University（香港理工大学）

Jiehong Lin, Zewei Wei, Yabin Zhang, Kui Jia

备注：: Accepted by ICCV2023. Project Page: https://github.com/JiehongLin/VI-Net

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对6D姿态估计中SO(3)空间旋转学习难的问题，提出VI-Net将旋转解耦为视点与平面内旋转，基于SPA-SConv构建球面特征金字塔实现等变特征提取，在类别级6D姿态估计任务上精度大幅超越现有方法。

摘要：

在6D物体姿态估计任务中，从RGB-D物体观测中估计高精度旋转是一项巨大挑战，原因在于SO(3)非线性空间的学习难度较高。本文提出一种新型旋转估计网络，命名为VI-Net，通过将旋转解耦为视点旋转与平面内旋转的组合，降低了任务难度。具体而言，VI-Net将特征学习建立在球面之上，设置两个独立分支分别估计这两个分解后的旋转：其中V-Branch（视点分支）通过对球面信号进行二分类学习视点旋转，另一个I-Branch（平面内分支）则通过将信号转换为从天顶方向观测的形式，估计平面内旋转。为处理球面信号，本文基于全新设计的SPAtial Spherical Convolution（空间球面卷积，简称SPA-SConv）构建了球面特征金字塔网络，该卷积通过特征填充解决了球面信号的边界问题，并通过对称卷积操作实现了视点等变的特征提取。我们将提出的VI-Net应用于具有挑战性的类别级6D物体姿态估计任务，该任务无需可用CAD模型即可预测未知物体的姿态；在基准数据集上的实验验证了方法的有效性，在高精度指标下，该方法的性能大幅优于现有方法。

英文摘要：

Rotation estimation of high precision from an RGB-D object observation is a huge challenge in 6D object pose estimation, due to the difficulty of learning in the non-linear space of SO(3). In this paper, we propose a novel rotation estimation network, termed as VI-Net, to make the task easier by decoupling the rotation as the combination of a viewpoint rotation and an in-plane rotation. More specifically, VI-Net bases the feature learning on the sphere with two individual branches for the estimates of two factorized rotations, where a V-Branch is employed to learn the viewpoint rotation via binary classification on the spherical signals, while another I-Branch is used to estimate the in-plane rotation by transforming the signals to view from the zenith direction. To process the spherical signals, a Spherical Feature Pyramid Network is constructed based on a novel design of SPAtial Spherical Convolution (SPA-SConv), which settles the boundary problem of spherical signals via feature padding and realizesviewpoint-equivariant feature extraction by symmetric convolutional operations. We apply the proposed VI-Net to the challenging task of category-level 6D object pose estimation for predicting the poses of unknown objects without available CAD models; experiments on the benchmarking datasets confirm the efficacy of our method, which outperforms the existing ones with a large margin in the regime of high precision.

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。