Neurosymbolic Models for Computer Graphics

Simple item page
dc.contributor.authorRitchie, Danielen_US
dc.contributor.authorGuerrero, Paulen_US
dc.contributor.authorJones, R. Kennyen_US
dc.contributor.authorMitra, Niloy J.en_US
dc.contributor.authorSchulz, Adrianaen_US
dc.contributor.authorWillis, Karl D. D.en_US
dc.contributor.authorWu, Jiajunen_US
dc.contributor.editorBousseau, Adrienen_US
dc.contributor.editorTheobalt, Christianen_US
dc.date.accessioned2023-05-03T06:13:38Z
dc.date.available2023-05-03T06:13:38Z
dc.date.issued2023
dc.description.abstractProcedural models (i.e. symbolic programs that output visual data) are a historically-popular method for representing graphics content: vegetation, buildings, textures, etc. They offer many advantages: interpretable design parameters, stochastic variations, high-quality outputs, compact representation, and more. But they also have some limitations, such as the difficulty of authoring a procedural model from scratch. More recently, AI-based methods, and especially neural networks, have become popular for creating graphic content. These techniques allow users to directly specify desired properties of the artifact they want to create (via examples, constraints, or objectives), while a search, optimization, or learning algorithm takes care of the details. However, this ease of use comes at a cost, as it's often hard to interpret or manipulate these representations. In this state-of-the-art report, we summarize research on neurosymbolic models in computer graphics: methods that combine the strengths of both AI and symbolic programs to represent, generate, and manipulate visual data. We survey recent work applying these techniques to represent 2D shapes, 3D shapes, and materials & textures. Along the way, we situate each prior work in a unified design space for neurosymbolic models, which helps reveal underexplored areas and opportunities for future research.en_US
dc.description.documenttypestar
dc.description.number2
dc.description.sectionheadersState of the Art Reports
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume42
dc.identifier.doi10.1111/cgf.14775
dc.identifier.issn1467-8659
dc.identifier.pages545-568
dc.identifier.pages24 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14775
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14775
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies -> Shape modeling; Reflectance modeling; Texturing; Neural networks; Computer vision; Software and its engineering -> Domain specific languages; Programming by example
dc.subjectComputing methodologies
dc.subjectShape modeling
dc.subjectReflectance modeling
dc.subjectTexturing
dc.subjectNeural networks
dc.subjectComputer vision
dc.subjectSoftware and its engineering
dc.subjectDomain specific languages
dc.subjectProgramming by example
dc.titleNeurosymbolic Models for Computer Graphicsen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
v42i2pp545-568_cgf14775.pdf
Size:
19.81 MB
Format:
Adobe Portable Document Format
Download
Collections
EG 2023 - STARs (CGF 42-2)