File Download

There are no files associated with this item.

  • Find it @ UNIST can give you direct access to the published full text of this article. (UNISTARs only)
Related Researcher

백승렬

Baek, Seungryul
UNIST VISION AND LEARNING LAB.
Read More

Views & Downloads

Detailed Information

Cited time in webofscience Cited time in scopus
Metadata Downloads

Full metadata record

DC Field Value Language
dc.citation.conferencePlace IS -
dc.citation.endPage 677 -
dc.citation.startPage 660 -
dc.citation.title European Conference on Computer Vision -
dc.contributor.author Cha, Junuk -
dc.contributor.author Saqlain, Muhammad -
dc.contributor.author Kim, GeonU -
dc.contributor.author Shin, Mingyu -
dc.contributor.author Baek, Seungryul -
dc.date.accessioned 2024-01-31T19:39:45Z -
dc.date.available 2024-01-31T19:39:45Z -
dc.date.created 2023-09-26 -
dc.date.issued 2022-10-25 -
dc.description.abstract Estimating 3D poses and shapes in the form of meshes from monocular RGB images is challenging. Obviously, it is more difficult than estimating 3D poses only in the form of skeletons or heatmaps. When interacting persons are involved, the 3D mesh reconstruction becomes more challenging due to the ambiguity introduced by person-to-person occlusions. To tackle the challenges, we propose a coarse-to-fine pipeline that benefits from 1) inverse kinematics from the occlusion-robust 3D skeleton estimation and 2) Transformer-based relation-aware refinement techniques. In our pipeline, we first obtain occlusion-robust 3D skeletons for multiple persons from an RGB image. Then, we apply inverse kinematics to convert the estimated skeletons to deformable 3D mesh parameters. Finally, we apply the Transformer-based mesh refinement that refines the obtained mesh parameters considering intra- and inter-person relations of 3D meshes. Via extensive experiments, we demonstrate the effectiveness of our method, outperforming state-of-the-arts on 3DPW, MuPoTS and AGORA datasets. -
dc.identifier.bibliographicCitation European Conference on Computer Vision, pp.660 - 677 -
dc.identifier.doi 10.1007/978-3-031-20065-6_38 -
dc.identifier.scopusid 2-s2.0-85144538356 -
dc.identifier.uri https://scholarworks.unist.ac.kr/handle/201301/75301 -
dc.language 영어 -
dc.publisher Springer Science and Business Media Deutschland GmbH -
dc.title Multi-Person 3D Pose andShape Estimation viaInverse Kinematics andRefinement -
dc.type Conference Paper -
dc.date.conferenceDate 2022-10-23 -

qrcode

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.