Academic Journal
Προβολή σε EDS

Approximating Procedural Models of 3D Shapes with Neural Networks.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Approximating Procedural Models of 3D Shapes with Neural Networks.
Συγγραφείς: Hossain, Ishtiaque, Shen, I‐Chao, van Kaick, Oliver
Πηγή: Computer Graphics Forum; May2025, Vol. 44 Issue 2, p1-15, 15p
Θεματικοί όροι: Artificial neural networks, Three-dimensional modeling, Three-dimensional imaging, Parametric modeling, Mathematical models, Geometric shapes
Περίληψη: Procedural modeling is a popular technique for 3D content creation and offers a number of advantages over alternative techniques for modeling 3D shapes. However, given a procedural model, predicting the procedural parameters of existing data provided in different modalities can be challenging. This is because the data may be in a different representation than the one generated by the procedural model, and procedural models are usually not invertible, nor are they differentiable. In this paper, we address these limitations and introduce an invertible and differentiable representation for procedural models. We approximate parameterized procedures with a neural network architecture NNProc that learns both the forward and inverse mapping of the procedural model by aligning the latent spaces of shape parameters and shapes. The network is trained in a manner that is agnostic to the inner workings of the procedural model, implying that models implemented in different languages or systems can be used. We demonstrate how the proposed representation can be used for both forward and inverse procedural modeling. Moreover, we show how NNProc can be used in conjunction with optimization for applications such as shape reconstruction from an image or a 3D Gaussian Splatting. [ABSTRACT FROM AUTHOR]
Copyright of Computer Graphics Forum is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Βάση Δεδομένων: Complementary Index
FullText Links:
  – Type: other
Text:
  Availability: 0
Header DbId: edb
DbLabel: Complementary Index
An: 186773086
RelevancyScore: 994
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 993.548583984375
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Approximating Procedural Models of 3D Shapes with Neural Networks.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Hossain%2C+Ishtiaque%22">Hossain, Ishtiaque</searchLink><br /><searchLink fieldCode="AR" term="%22Shen%2C+I‐Chao%22">Shen, I‐Chao</searchLink><br /><searchLink fieldCode="AR" term="%22van+Kaick%2C+Oliver%22">van Kaick, Oliver</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Computer Graphics Forum; May2025, Vol. 44 Issue 2, p1-15, 15p
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Three-dimensional+modeling%22">Three-dimensional modeling</searchLink><br /><searchLink fieldCode="DE" term="%22Three-dimensional+imaging%22">Three-dimensional imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Parametric+modeling%22">Parametric modeling</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+models%22">Mathematical models</searchLink><br /><searchLink fieldCode="DE" term="%22Geometric+shapes%22">Geometric shapes</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Procedural modeling is a popular technique for 3D content creation and offers a number of advantages over alternative techniques for modeling 3D shapes. However, given a procedural model, predicting the procedural parameters of existing data provided in different modalities can be challenging. This is because the data may be in a different representation than the one generated by the procedural model, and procedural models are usually not invertible, nor are they differentiable. In this paper, we address these limitations and introduce an invertible and differentiable representation for procedural models. We approximate parameterized procedures with a neural network architecture NNProc that learns both the forward and inverse mapping of the procedural model by aligning the latent spaces of shape parameters and shapes. The network is trained in a manner that is agnostic to the inner workings of the procedural model, implying that models implemented in different languages or systems can be used. We demonstrate how the proposed representation can be used for both forward and inverse procedural modeling. Moreover, we show how NNProc can be used in conjunction with optimization for applications such as shape reconstruction from an image or a 3D Gaussian Splatting. [ABSTRACT FROM AUTHOR]
– Name: Abstract
  Label:
  Group: Ab
  Data: <i>Copyright of Computer Graphics Forum is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=186773086
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1111/cgf.70024
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 15
        StartPage: 1
    Subjects:
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Three-dimensional modeling
        Type: general
      – SubjectFull: Three-dimensional imaging
        Type: general
      – SubjectFull: Parametric modeling
        Type: general
      – SubjectFull: Mathematical models
        Type: general
      – SubjectFull: Geometric shapes
        Type: general
    Titles:
      – TitleFull: Approximating Procedural Models of 3D Shapes with Neural Networks.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Hossain, Ishtiaque
      – PersonEntity:
          Name:
            NameFull: Shen, I‐Chao
      – PersonEntity:
          Name:
            NameFull: van Kaick, Oliver
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 05
              Text: May2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 01677055
          Numbering:
            – Type: volume
              Value: 44
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Computer Graphics Forum
              Type: main
ResultId 1