SE(3) 等变性与几何拓扑引导的类别级物体姿态估计
SE(3)-Equivariance with Geometric and Topological Guidance for Category-Level Object Pose Estimation
将 SE(3) 等变网络与几何/拓扑约束结合用于点云类别级姿态估计，其等变特征预测模块可迁移到其他需要视角一致性的 3D 任务（如点云配准、新视角合成）。
原文依据 SEGPose leverages geometric, topological information, and SE(3)-equivariance, enhancing the network's accuracy in pose prediction.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论物体姿态估计是具身机器人有效交互的关键任务。类别级物体姿态估计为机器人估计未知物体的姿态提供了途径。然而，仅从点云估计物体姿态仍然具有挑战性。本文提出 SEGPose，一种基于点云的新型类别级物体姿态估计方法。与以往方法不同，SEGPose 利用几何信息、拓扑信息以及 SE(3) 等变性，提升网络姿态预测的准确性。为利用几何与拓扑特征，我们提出一种基于约束的特征提取与三维重建方法，实现有效的物体形状重建。我们还设计了一个 SE(3) 等变特征预测网络，以在跨视角下一致地处理姿态变换，提高姿态精度。在基准数据集上的实验结果表明，SEGPose 优于当前所有基于点云的类别级姿态估计方法。此外，我们将 SEGPose 应用于真实场景中的机器人抓取任务，结果表明 SEGPose 展现出优异的泛化能力。
英文原文摘要 1209 字符
Object pose estimation is a key task for embodied robots, enabling them to interact with objects effectively. Category-level object pose estimation provides a way for robots to estimate the pose of unknown objects. However, estimating object pose from point clouds alone remains challenging. In this paper, we introduce SEGPose, a novel category-level object pose estimation method based on point clouds. Unlike previous methods, SEGPose leverages geometric, topological information, and SE(3)-equivariance, enhancing the network's accuracy in pose prediction. To utilize geometric and topological features, we propose a constraint-based feature extraction and 3D reconstruction method, enabling effective object shape reconstruction. We also design an SE(3)-equivariance feature prediction network to handle pose transformations consistently across viewpoints, improving pose accuracy. Experimental results on benchmark datasets show that SEGPose outperforms all current category-level pose estimation methods based on point clouds. Additionally, we apply the SEGPose to the robotic grasping tasks in real-world scenarios, and the results indicate that SEGPose exhibits excellent generalization capabilities.