SCAPO：基于单次三维观测的自监督类别级关节位姿估计
SCAPO: Self-Supervised Category-Level Articulated Pose Estimation from a Single 3D Observation
用 SE(3) 等变向量神经元自编码器把单帧 RGB-D 观测对齐到共享规范空间，再用关节感知的混合蒙皮建模部件运动，为单次观测下的关节物体建模提供了可复用的表示学习范式。
原文依据 an SE(3)-equivariant vector-neuron autoencoder to factor out global pose and align diverse instances into a shared canonical space
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有从单次三维观测估计类别级物体关节结构的方法往往依赖稠密监督、多帧输入或 CAD 模板，并且仍难以将几何与关节结构解耦，也难以恢复显式的关节参数。我们提出 SCAPO，一个自监督框架，能够从单次 RGB-D 观测中估计规范几何、刚性部件分割以及关节的枢轴、轴与关节状态，且无需真值标签或类别专用模型。SCAPO 首先使用 SE(3) 等变向量神经元自编码器分离出全局位姿，并将多样实例对齐到共享的规范空间。在该对齐后的形状上，我们设计了关节感知的混合蒙皮模块来建模部件运动。我们通过观测形状与规范形状之间的循环重建，以及与可学习规范模板的跨空间对齐来学习这一表示，从而将共享的类别几何与实例特有的残差形状解耦。在合成与真实关节物体数据集上的实验表明，SCAPO 能够恢复一致的部件结构和准确的关节参数，并优于所有自监督基线。
英文原文摘要 1190 字符
Existing methods for category-level object articulation from a single 3D observation often rely on dense supervision, multi-frame inputs, or CAD templates, and still struggle to disentangle geometry from articulation or to recover explicit joint parameters. We propose SCAPO , a self-supervised framework that estimates canonical geometry, rigid part segmentation, and joint pivots, axes, and articulation states from a single RGB-D observation without ground-truth labels or category-specific models. Our SCAPO first uses an SE(3)-equivariant vector-neuron autoencoder to factor out global pose and align diverse instances into a shared canonical space. On this aligned shape, a joint-aware blend-skinning module is then designed to model part motion. We learn this representation through cycle reconstruction between observed and canonical shapes and cross-space alignment with a learnable canonical template that decouples shared category geometry from instance-specific residual shape. Experiments on synthetic and real articulated-object datasets show that our SCAPO recovers consistent part structure and accurate articulation parameters and outperforms all self-supervised baselines.