Joint Hand and Object Pose Estimation from a Single RGB Image using High-level 2D Constraints

Simple item page
dc.contributor.authorSong, Hao-Xuanen_US
dc.contributor.authorMu, Tai-Jiangen_US
dc.contributor.authorMartin, Ralph R.en_US
dc.contributor.editorUmetani, Nobuyukien_US
dc.contributor.editorWojtan, Chrisen_US
dc.contributor.editorVouga, Etienneen_US
dc.date.accessioned2022-10-04T06:41:24Z
dc.date.available2022-10-04T06:41:24Z
dc.date.issued2022
dc.description.abstractJoint pose estimation of human hands and objects from a single RGB image is an important topic for AR/VR, robot manipulation, etc. It is common practice to determine both poses directly from the image; some recent methods attempt to improve the initial poses using a variety of contact-based approaches. However, few methods take the real physical constraints conveyed by the image into consideration, leading to less realistic results than the initial estimates. To overcome this problem, we make use of a set of high-level 2D features which can be directly extracted from the image in a new pipeline which combines contact approaches and these constraints during optimization. Our pipeline achieves better results than direct regression or contactbased optimization: they are closer to the ground truth and provide high quality contact.en_US
dc.description.number7
dc.description.sectionheadersImage Detection and Understanding
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume41
dc.identifier.doi10.1111/cgf.14685
dc.identifier.issn1467-8659
dc.identifier.pages383-394
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14685
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14685
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Reconstruction
dc.subjectComputing methodologies → Reconstruction
dc.titleJoint Hand and Object Pose Estimation from a Single RGB Image using High-level 2D Constraintsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
v41i7pp383-394.pdf
Size:
2 MB
Format:
Adobe Portable Document Format
Download
Collections
41-Issue 7