Learning Generative Models of 3D Structures

Simple item page
dc.contributor.authorChaudhuri, Siddharthaen_US
dc.contributor.authorRitchie, Danielen_US
dc.contributor.authorWu, Jiajunen_US
dc.contributor.authorXu, Kaien_US
dc.contributor.authorZhang, Haoen_US
dc.contributor.editorMantiuk, Rafal and Sundstedt, Veronicaen_US
dc.date.accessioned2020-05-24T13:45:11Z
dc.date.available2020-05-24T13:45:11Z
dc.date.issued2020
dc.description.abstract3D models of objects and scenes are critical to many academic disciplines and industrial applications. Of particular interest is the emerging opportunity for 3D graphics to serve artificial intelligence: computer vision systems can benefit from syntheticallygenerated training data rendered from virtual 3D scenes, and robots can be trained to navigate in and interact with real-world environments by first acquiring skills in simulated ones. One of the most promising ways to achieve this is by learning and applying generative models of 3D content: computer programs that can synthesize new 3D shapes and scenes. To allow users to edit and manipulate the synthesized 3D content to achieve their goals, the generative model should also be structure-aware: it should express 3D shapes and scenes using abstractions that allow manipulation of their high-level structure. This state-of-theart report surveys historical work and recent progress on learning structure-aware generative models of 3D shapes and scenes. We present fundamental representations of 3D shape and scene geometry and structures, describe prominent methodologies including probabilistic models, deep generative models, program synthesis, and neural networks for structured data, and cover many recent methods for structure-aware synthesis of 3D shapes and indoor scenes.en_US
dc.description.documenttypestar
dc.description.number2
dc.description.sectionheadersState of the Art Reports
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume39
dc.identifier.doi10.1111/cgf.14020
dc.identifier.issn1467-8659
dc.identifier.pages643-666
dc.identifier.urihttps://doi.org/10.1111/cgf.14020
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14020
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/]
dc.subjectComputing methodologies
dc.subjectStructure
dc.subjectaware generative models
dc.subjectRepresentation of structured data
dc.subjectDeep learning
dc.subjectNeural networks
dc.subjectShape and scene synthesis
dc.subjectHierarchical models
dc.titleLearning Generative Models of 3D Structuresen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
v39i2pp643-666.pdf
Size:
8.01 MB
Format:
Adobe Portable Document Format
Download
Collections
EG 2020 - STARs (CGF 39-2)