VALSE

VALSE 首页 活动通知 查看内容

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 ...

2023-10-27 14:34| 发布者: 程一-计算所| 查看: 373| 评论: 0

摘要: 为了使得视觉与学习领域相关从业者快速及时地了解领域的最新发展动态和前沿技术进展,VALSE最新推出了《论文速览》栏目,将在每周发布一至两篇顶会顶刊论文的录制视频,对单个前沿工作进行细致讲解。本期VALSE 论文 ...

为了使得视觉与学习领域相关从业者快速及时地了解领域的最新发展动态和前沿技术进展,VALSE最新推出了《论文速览》栏目,将在每周发布一至两篇顶会顶刊论文的录制视频,对单个前沿工作进行细致讲解。本期VALSE 论文速览选取了来自清华大学、复旦大学、深圳大学、快手科技、北京大学在自监督铰接物体位姿估计的工作。该工作由弋力老师指导,刘雪怡同学录制。


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)


活动参与方式

1、VALSE每周举行的Webinar活动依托B站直播平台进行,欢迎在B站搜索VALSE_Webinar关注我们!

直播地址:

https://live.bilibili.com/22300737;

历史视频观看地址:

https://space.bilibili.com/562085182/ 


2、VALSE Webinar活动通常每周三晚上20:00进行,但偶尔会因为讲者时区问题略有调整,为方便您参加活动,请关注VALSE微信公众号:valse_wechat 或加入VALSE QQ S群,群号:317920537);


*注:申请加入VALSE QQ群时需验证姓名、单位和身份缺一不可。入群后,请实名,姓名身份单位。身份:学校及科研单位人员T;企业研发I;博士D;硕士M。


3、VALSE微信公众号一般会在每周四发布下一周Webinar报告的通知。


4您也可以通过访问VALSE主页:http://valser.org/ 直接查看Webinar活动信息。Webinar报告的PPT(经讲者允许后),会在VALSE官网每期报告通知的最下方更新。

小黑屋|手机版|Archiver|Vision And Learning SEminar

GMT+8, 2024-7-18 22:37 , Processed in 0.015776 second(s), 14 queries .

Powered by Discuz! X3.4

Copyright © 2001-2020, Tencent Cloud.

返回顶部