用记忆库提升物体姿态估计的泛化能力，支持多样化实例
MemPose: Category-level Object Pose Estimation with Memory
- 引入外部记忆缓冲区存储并动态更新物体结构特征
- 在4个基准上超越现有最先进方法，显著提升泛化性能
- 适合需要处理多样物体实例的工业场景应用
为实现鲁棒且可泛化的类别级物体姿态估计，现有方法多采用参数化形式学习数据有效表示，但主要将类别级模式编码为固定形状先验或静态参数权重，限制了对高度多样化实例的扩展性。本文从记忆中心视角重新思考类别级姿态估计，提出MemPose——一种将类别级几何记忆显式融入姿态估计流程的记忆增强框架。引入外部记忆缓冲区，用于存储并动态更新先前观测实例的结构表征，使模型能利用累积经验支持当前感知。在四个挑战性基准（REAL275、CAMERA25、Housecat6D 和 Wild6D）上的大量实验表明，所提方法优于以往最先进方法。
原文摘要 · Abstract (English)
In the pursuit of robust and generalizable category-level object pose estimation, most existing methods adopt parametric formulations that learn effective representations from data, yet they primarily encode category-level patterns into fixed shape priors or static parameter weights, which limits their scalability to highly diverse instances. In this paper, we rethink category-level pose estimation from a memory-centric perspective and present MemPose, a memory-augmented framework that explicitly incorporates category-level geometric memory into the pose estimation pipeline. We introduce an external memory buffer that stores and dynamically updates structural representations from previously observed instances, enabling the model to leverage accumulated experience to support current perception. Extensive experiments on four challenging benchmarks (REAL275, CAMERA25, Housecat6D and Wild6D) demonstrate the superiority of our proposed method over previous state-of-the-art approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。