DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wang, Kai | ko |
dc.contributor.author | Guerrero, Paul | ko |
dc.contributor.author | Kim, Vladimir G. | ko |
dc.contributor.author | Chaudhuri, Siddhartha | ko |
dc.contributor.author | Sung, Minhyuk | ko |
dc.contributor.author | Ritchie, Daniel | ko |
dc.date.accessioned | 2022-11-15T06:00:44Z | - |
dc.date.available | 2022-11-15T06:00:44Z | - |
dc.date.created | 2022-11-13 | - |
dc.date.created | 2022-11-13 | - |
dc.date.created | 2022-11-13 | - |
dc.date.created | 2022-11-13 | - |
dc.date.issued | 2022-10 | - |
dc.identifier.citation | European Conference on Computer Vision, ECCV 2022, pp.610 - 626 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/10203/299638 | - |
dc.description.abstract | We present the Shape Part Slot Machine, a new method for assembling novel 3D shapes from existing parts by performing contact-based reasoning. Our method represents each shape as a graph of “slots,” where each slot is a region of contact between two shape parts. Based on this representation, we design a graph-neural-network-based model for generating new slot graphs and retrieving compatible parts, as well as a gradient-descent-based optimization scheme for assembling the retrieved parts into a complete shape that respects the generated slot graph. This approach does not require any semantic part labels; interestingly, it also does not require complete part geometries—reasoning about the slots proves sufficient to generate novel, high-quality 3D shapes. We demonstrate that our method generates shapes that outperform existing modeling-by-assembly approaches regarding quality, diversity, and structural complexity. | - |
dc.language | English | - |
dc.publisher | European Conference on Computer Vision | - |
dc.title | The Shape Part Slot Machine: Contact-Based Reasoning for Generating 3D Shapes from Parts | - |
dc.type | Conference | - |
dc.identifier.wosid | 000899240500035 | - |
dc.identifier.scopusid | 2-s2.0-85144567889 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 610 | - |
dc.citation.endingpage | 626 | - |
dc.citation.publicationname | European Conference on Computer Vision, ECCV 2022 | - |
dc.identifier.conferencecountry | IS | - |
dc.identifier.conferencelocation | Tel Aviv | - |
dc.identifier.doi | 10.1007/978-3-031-20062-5_35 | - |
dc.contributor.localauthor | Sung, Minhyuk | - |
dc.contributor.nonIdAuthor | Wang, Kai | - |
dc.contributor.nonIdAuthor | Guerrero, Paul | - |
dc.contributor.nonIdAuthor | Kim, Vladimir G. | - |
dc.contributor.nonIdAuthor | Chaudhuri, Siddhartha | - |
dc.contributor.nonIdAuthor | Ritchie, Daniel | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.