ComPose：面向鲁棒类别级物体姿态估计的统一补全-姿态框架
ComPose: A Unified Completion-Pose Framework for Robust Category-Level Object Pose Estimation
将点云补全与类别级姿态估计统一到一个端到端框架中，通过渐进式关键点补全和几何关系一致性损失，避免了两阶段方法的误差累积，为处理不完整点云的姿态估计提供了可复用的设计思路。
原文依据 we propose ComPose, a novel unified framework that tightly integrates shape completion to provide complete geometric cues for enhanced pose estimation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论类别级物体姿态估计旨在预测特定类别中任意物体的姿态和尺寸。现有方法难以应对观测点云固有的不完整性，这限制了它们捕获完整物体形状以进行鲁棒姿态推理的能力。尽管点云补全提供了一种有前景的解决方案，但将其朴素地视为对部分观测的独立预处理步骤会引入累积误差和额外计算开销，最终阻碍了准确性和效率。为解决这些挑战，我们提出了 ComPose，一种新颖的统一框架，紧密集成形状补全以为增强的姿态估计提供完整的几何线索。ComPose 的核心是基于关键点的渐进式补全模块，该模块通过渐进式预测稀疏关键点集及其周围密集点集来恢复完整形状表示，使关键点能够捕获整体物体几何。几何关系编码模块进一步利用局部和全局几何上下文丰富关键点特征。此外，我们引入了一种新颖的几何关系一致性损失，以强制观测关键点与其预测的 NOCS 坐标之间的结构对齐，确保全局一致的坐标变换。在标准基准上的大量实验表明，我们的方法在不依赖类别级形状先验的情况下优于最优方法。
英文原文摘要 1501 字符
Category-level object pose estimation aims to predict the pose and size of arbitrary objects in specific categories. Existing methods struggle with the inherent incompleteness of observed point clouds, which limits their ability to capture complete object shapes for robust pose reasoning. While point cloud completion offers a promising solution, naively treating it as a separate preprocessing step for partial observations introduces compounding errors and additional computational overhead, ultimately hindering both accuracy and efficiency. To address these challenges, we propose ComPose, a novel unified framework that tightly integrates shape completion to provide complete geometric cues for enhanced pose estimation. At the core of ComPose is a keypoint-based progressive completion module, which recovers full shape representations by progressively predicting a sparse set of keypoints and their surrounding dense point sets, empowering the keypoints to capture holistic object geometries. A geometric relation encoding module further enriches keypoint features with both local and global geometric context. In addition, we introduce a novel geometric relation consistency loss to enforce structural alignment between observed keypoints and their predicted NOCS coordinates, ensuring globally coherent coordinate transformations. Extensive experiments on standard benchmarks demonstrate that our method outperforms state-of-the-art approaches without relying on category-level shape priors.