VALSE 论文速览 第142期：基于部件级别SE(3)等变特征的自监督铰接物体位姿估计 ...

论文题目：Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance

作者列表：

刘雪怡 (清华大学)，张冀 (复旦大学)，胡瑞珍 (深圳大学)，黄海斌 (快手科技)、王鹤 (北京大学)、弋力 (清华大学)

B站观看网址：

https://www.bilibili.com/video/BV1Lw411z7pj/

论文摘要：

Category-level articulated object pose estimation aims to estimate a hierarchy of articulation-aware object poses of an unseen articulated object from a known category. To reduce the heavy annotations needed for supervised learning methods, we present a novel self-supervised strategy that solves this problem without any human labels. Our key idea is to factorize canonical shapes and articulated object poses from input articulated shapes through part-level equivariant shape analysis. Specifically, we first introduce the concept of part-level SE(3) equivariance and devise a network to learn features of such property. Then, through a carefully designed fine-grained pose-shape disentanglement strategy, we expect that canonical spaces to support pose estimation could be induced automatically. Thus, we could further predict articulated object poses as per-part rigid transformations describing how parts transform from their canonical part spaces to the camera space. Extensive experiments demonstrate the effectiveness of our method on both complete and partial point clouds from synthetic and real articulated object datasets.

论文信息：

[1] Xueyi Liu, Ji Zhang, Ruizhen Hu, Haibin Huang, He Wang, Li Yi, Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance, In ICLR, 2023.

论文链接：

[https://arxiv.org/abs/2302.14268]

代码链接：

[https://github.com/Meowuu7/equi-articulated-pose]

视频讲者简介：

刘雪怡，清华大学计算机系本科生，研究兴趣目前集中在3D视觉领域。

特别鸣谢本次论文速览主要组织者：

月度轮值AC：焦剑波 (伯明翰大学)

季度轮值AC：叶茫 (武汉大学)