Show simple item record

dc.contributor.authorLiu, Zhijian
dc.contributor.authorFreeman, William T
dc.contributor.authorTenenbaum, Joshua B
dc.contributor.authorWu, Jiajun
dc.date.accessioned2020-12-11T15:44:53Z
dc.date.available2020-12-11T15:44:53Z
dc.date.issued2018-10
dc.date.submitted2018-09
dc.identifier.isbn9783030012571
dc.identifier.isbn9783030012588
dc.identifier.issn0302-9743
dc.identifier.issn1611-3349
dc.identifier.urihttps://hdl.handle.net/1721.1/128814
dc.description.abstractObjects are made of parts, each with distinct geometry, physics, functionality, and affordances. Developing such a distributed, physical, interpretable representation of objects will facilitate intelligent agents to better explore and interact with the world. In this paper, we study physical primitive decomposition—understanding an object through its components, each with physical and geometric attributes. As annotated data for object parts and physics are rare, we propose a novel formulation that learns physical primitives by explaining both an object’s appearance and its behaviors in physical events. Our model performs well on block towers and tools in both synthetic and real scenarios; we also demonstrate that visual and physical observations often provide complementary signals. We further present ablation and behavioral studies to better understand our model and contrast it with human performance.en_US
dc.description.sponsorshipNSF (Grant 1231216)en_US
dc.description.sponsorshipONR MURI (Grant N00014-16-1-2007)en_US
dc.language.isoen
dc.publisherSpringer International Publishingen_US
dc.relation.isversionofhttp://dx.doi.org/10.1007/978-3-030-01258-8_1en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourceSpringeren_US
dc.titlePhysical Primitive Decompositionen_US
dc.typeBooken_US
dc.identifier.citationLiu, Zhijian et al. "Physical Primitive Decomposition." European Conference on Computer Vision, September 2018, Munich, Germany, Springer International Publishing, October 2018. © 2018 Springer Natureen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Brain and Cognitive Sciencesen_US
dc.relation.journalEuropean Conference on Computer Visionen_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dc.date.updated2019-05-28T12:11:56Z
dspace.date.submission2019-05-28T12:11:58Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record