| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://dragonlong.github.io/equi-pose/
x-github-request-id: 7B17:328FD3:81D790:91D056:6951CA60
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 00:25:04 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210055-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766967904.354173,VS0,VE201
vary: Accept-Encoding
x-fastly-request-id: 089f174d42b1ef02acb21bdf630cb86e595f13bf
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Sat, 22 Jan 2022 06:43:54 GMT
access-control-allow-origin: *
etag: W/"61eba7aa-2eb6"
expires: Mon, 29 Dec 2025 00:35:04 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: CFAF:292AC1:8193F7:918EBB:6951CA5F
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 00:25:04 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210055-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766967905.568767,VS0,VE219
vary: Accept-Encoding
x-fastly-request-id: 3d29d12362b08bb56a518a7dea5fb0f45037d8b6
content-length: 3670
Self-supervised Pose with SE(3) Equivariance
Leveraging SE(3) Equivariance for Self-Supervised
Leveraging SE(3) Equivariance for Self-Supervised
Category-Level Object Pose Estimation
Xiaolong Li1
Yijia Weng2,4
Li Yi3
Leonidas Guibas4
A. Lynn Abbott1
Shuran Song5
He Wang2
1Virginia Tech 2Peking University 3Tsinghua University 4Stanford University 5Columbia University
Abstract
Category-level object pose estimation aims to find 6D object poses of previously unseen object instances from known categories without access to object CAD models. To reduce the huge amount of pose annotations needed for category-level learning, we propose for the first time a self-supervised learning framework to estimate category-level 6D object pose from single 3D point clouds. During training, our method assumes no ground-truth pose annotations, no CAD models, and no multi-view supervision. The key to our method is to disentangle shape and pose through an invariant shape reconstruction module and an equivariant pose estimation module, empowered by SE(3) equivariant point cloud networks. The invariant shape reconstruction module learns to perform aligned reconstructions, yielding a category-level reference frame without using any annotations. In addition,the equivariant pose estimation module achieves category-level pose estimation accuracy that is comparable to some fully supervised methods. Extensive experiments demonstrate the effectiveness of our approach on both complete and partialdepth point clouds from the ModelNet40 benchmark, and on real depth point cloudsfrom the NOCS-REAL 275 dataset.Results on Category-Level 3D Pose Estimation(Complete Input)
Results on Category-Level 6D Pose Estimation(Partial Input)
Paper
BibTex
@article{li2021leveraging,
Author = {Li, Xiaolong and Weng, Yijia and Yi, Li and Guibas, Leonidas and Abbott, A Lynn and Song, Shuran and Wang, He},
Title = {Leveraging SE(3) Equivariance for Self-Supervised Category-Level Object Pose Estimation},
journal = {Thirty-Fifth Conference on Neural Information Processing Systems},
year = {2021}
}
Acknowledgments
This research is supported by a Vannevar Bush faculty fellowship, NSF grant IIS-1763268, and gifts from the Adobe and Autodesk Corporations. We appreciate resources provided by Advanced Research Computing in the Division of Information Technology at Virginia Tech. We also thank Dr. Haiwei Chen for the helpful chat over equivariant neural networks.Copyright © Xiaolong Li 2021