arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2504.15134cs.CV
收藏

实例自适应关键点学习与局部到全局几何聚合用于类别级物体姿态估计

Instance-Adaptive Keypoint Learning with Local-to-Global Geometric Aggregation for Category-Level Object Pose Estimation

Wuhan Institute of Technology(武汉理工大学);University of Science and Technology of China(中国科学技术大学);Peking University(北京大学)

Xiao Zhang, Lu Zou, Tao Lu, Yuan Yao, Zhangjin Huang, Guoping Wang

AI总结:

INKL-Pose通过实例自适应关键点学习与局部到全局几何聚合,实现类别级物体姿态估计的高精度与高效性。

摘要:

类别级物体姿态估计旨在从预定义类别中预测之前未见过的实例的6D姿态和尺寸,需要在多样化的物体实例上具有强大的泛化能力。尽管许多先前的方法试图缓解类内变化,但它们往往难以处理具有复杂几何结构或显著偏离标准形状的实例。为了解决这个问题,我们提出了INKL-Pose,一种新的类别级物体姿态估计框架,该框架实现了实例自适应关键点学习与局部到全局几何聚合。具体来说,我们的方法首先使用实例自适应关键点检测器预测语义一致且几何信息丰富的关键点,然后进行细化:(1) 一个局部关键点特征聚合器捕捉细粒度几何结构,以及(2) 一个使用双向Mamba的全局关键点特征聚合器以实现结构一致性。为了在Mamba中实现双向建模,我们引入了一种简单但有效的特征序列翻转策略,该策略在构建反向特征序列时保持空间一致性。此外,我们设计了一个表面损失和一个分离损失,以鼓励关键点分布的均匀覆盖和空间多样性。最终的关键点被映射到规范空间以进行6D姿态和尺寸回归。在CAMERA25、REAL275和HouseCat6D上的大量实验表明,INKL-Pose在16.7M参数和NVIDIA RTX 4090D GPU上以36 FPS的速度实现了最先进的性能。

英文摘要:

Category-level object pose estimation aims to predict the 6D pose and size of previously unseen instances from predefined categories, requiring strong generalization across diverse object instances. Although many previous methods attempt to mitigate intra-class variations, they often struggle with instances exhibiting complex geometries or significant deviations from canonical shapes. To address this issue, we propose INKL-Pose, a novel category-level object pose estimation framework that enables INstance-adaptive Keypoint Learning with local-to-global geometric aggregation. Specifically, our method first predicts semantically consistent and geometrically informative keypoints using an Instance-Adaptive Keypoint Detector, then refines them: (1) a Local Keypoint Feature Aggregator capturing fine-grained geometries, and (2) a Global Keypoint Feature Aggregator using bidirectional Mamba for structural consistency. To enable bidirectional modeling in Mamba, we introduce a simple yet effective Feature Sequence Flipping strategy that preserves spatial coherence while constructing backward feature sequence. Additionally, we design a surface loss and a separation loss to encourage uniform coverage and spatial diversity in keypoint distribution. The resulting keypoints are mapped to a canonical space for 6D pose and size regression. Extensive experiments on CAMERA25, REAL275, and HouseCat6D show that INKL-Pose achieves state-of-the-art performance with 16.7M parameters and runs at 36 FPS on an NVIDIA RTX 4090D GPU.

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。

↑