dc.contributor.author | Sundt, Peder Bergebakken | |
dc.contributor.author | Theoharis, Theoharis | |
dc.date.accessioned | 2023-12-05T09:00:47Z | |
dc.date.available | 2023-12-05T09:00:47Z | |
dc.date.created | 2023-09-05T12:05:31Z | |
dc.date.issued | 2023 | |
dc.identifier.citation | Computers & graphics. 2023, 115 122-136. | en_US |
dc.identifier.issn | 0097-8493 | |
dc.identifier.uri | https://hdl.handle.net/11250/3105940 | |
dc.description.abstract | We propose Medial Atom Ray Fields (MARFs), a novel neural object representation that enables accurate differentiable surface rendering with a single network evaluation per camera ray. Existing neural ray fields struggle with multi-view consistency and representing surface discontinuities. MARFs address both using a medial shape representation, a dual representation of solid geometry that yields cheap geometrically grounded surface normals, in turn enabling computing analytical curvature despite the network having no second derivative. MARFs map a camera ray to multiple medial intersection candidates, subject to ray-sphere intersection testing. We illustrate how the learned medial shape quantities applies to sub-surface scattering, part segmentation, and aid representing a space of articulated shapes. Able to learn a space of shape priors, MARFs may prove useful for tasks like shape retrieval and shape completion, among others. Code and data can be found at https://github.com/pbsds/MARF. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Elsevier B. V. | en_US |
dc.rights | Navngivelse 4.0 Internasjonal | * |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/deed.no | * |
dc.title | MARF: The Medial Atom Ray Field object representation | en_US |
dc.title.alternative | MARF: The Medial Atom Ray Field object representation | en_US |
dc.type | Peer reviewed | en_US |
dc.type | Journal article | en_US |
dc.description.version | publishedVersion | en_US |
dc.source.pagenumber | 122-136 | en_US |
dc.source.volume | 115 | en_US |
dc.source.journal | Computers & graphics | en_US |
dc.identifier.doi | 10.1016/j.cag.2023.06.032 | |
dc.identifier.cristin | 2172485 | |
cristin.ispublished | true | |
cristin.fulltext | original | |
cristin.qualitycode | 2 | |