SO(3)-Pose: SO(3)-Equivariance Learning for 6D Object Pose Estimation

Simple item page
dc.contributor.authorPan, Haoranen_US
dc.contributor.authorZhou, Junen_US
dc.contributor.authorLiu, Yuanpengen_US
dc.contributor.authorLu, Xuequanen_US
dc.contributor.authorWang, Weimingen_US
dc.contributor.authorYan, Xuefengen_US
dc.contributor.authorWei, Mingqiangen_US
dc.contributor.editorUmetani, Nobuyukien_US
dc.contributor.editorWojtan, Chrisen_US
dc.contributor.editorVouga, Etienneen_US
dc.date.accessioned2022-10-04T06:41:23Z
dc.date.available2022-10-04T06:41:23Z
dc.date.issued2022
dc.description.abstract6D pose estimation of rigid objects from RGB-D images is crucial for object grasping and manipulation in robotics. Although RGB channels and the depth (D) channel are often complementary, providing respectively the appearance and geometry information, it is still non-trivial on how to fully benefit from the two cross-modal data. From the simple yet new observation, when an object rotates, its semantic label is invariant to the pose while its keypoint offset direction is variant to the pose. To this end, we present SO(3)-Pose, a new representation learning network to explore SO(3)-equivariant and SO(3)-invariant features from the depth channel for pose estimation. The SO(3)-invariant features facilitate to learn more distinctive representations for segmenting objects with similar appearance from RGB channels. The SO(3)-equivariant features communicate with RGB features to deduce the (missed) geometry for detecting keypoints of an object with the reflective surface from the depth channel. Unlike most of existing pose estimation methods, our SO(3)-Pose not only implements the information communication between the RGB and depth channels, but also naturally absorbs the SO(3)-equivariance geometry knowledge from depth images, leading to better appearance and geometry representation learning. Comprehensive experiments show that our method achieves the stateof- the-art performance on three benchmarks. Code is available at https://github.com/phaoran9999/SO3-Pose.en_US
dc.description.number7
dc.description.sectionheadersImage Detection and Understanding
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume41
dc.identifier.doi10.1111/cgf.14684
dc.identifier.issn1467-8659
dc.identifier.pages371-381
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14684
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14684
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Point-based models
dc.subjectComputing methodologies → Point
dc.subjectbased models
dc.titleSO(3)-Pose: SO(3)-Equivariance Learning for 6D Object Pose Estimationen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
v41i7pp371-381.pdf
Size:
2.89 MB
Format:
Adobe Portable Document Format
Download
Collections
41-Issue 7