Combining CNN Feature Extraction and Kolmogorov-Arnold Networks Regression for Procedural 3D Shape Generation

Simple item page
dc.contributor.authorManfredi, Gildaen_US
dc.contributor.authorCapece, Nicolaen_US
dc.contributor.authorErra, Ugoen_US
dc.contributor.authorGruosso, Antonioen_US
dc.contributor.editorComino Trinidad, Marcen_US
dc.contributor.editorMancinelli, Claudioen_US
dc.contributor.editorMaggioli, Filippoen_US
dc.contributor.editorRomanengo, Chiaraen_US
dc.contributor.editorCabiddu, Danielaen_US
dc.contributor.editorGiorgi, Danielaen_US
dc.date.accessioned2025-11-21T07:28:12Z
dc.date.available2025-11-21T07:28:12Z
dc.date.issued2025
dc.description.abstractGenerating 3D objects with complex, nonlinear shapes directly from images is still an open research area. To address this problem, several state-of-the-art methods use Deep Learning (DL) to predict a set of parameters from images, which are then used to generate the 3D geometry, leveraging the characteristics of procedural modeling. Recently, Kolmogorov-Arnold Networks (KANs) have emerged as an alternative to traditional Multilayer Perceptrons (MLPs) in DL, and have been successfully integrated into architectures such as Convolutional Neural Networks (CNNs), Graph Neural Networks, and Transformers. In this work, we propose a DL architecture consisting of a hybrid CNN-KAN network for parametric 3D model generation from images. The model combines the ability of KANs to capture complex nonlinear functions with the strong visual feature extraction capabilities of CNNs. The method is evaluated using both quantitative error metrics and qualitative visualizations comparing predicted shapes with ground truth, and its performance is compared against a more standard CNN-MLP architecture.en_US
dc.description.sectionheadersLearning-based Algorithms
dc.description.seriesinformationSmart Tools and Applications in Graphics - Eurographics Italian Chapter Conference
dc.identifier.doi10.2312/stag.20251327
dc.identifier.isbn978-3-03868-296-7
dc.identifier.issn2617-4855
dc.identifier.pages9 pages
dc.identifier.urihttps://doi.org/10.2312/stag.20251327
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/stag20251327
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Artificial intelligence; Modeling methodologies
dc.subjectComputing methodologies → Artificial intelligence
dc.subjectModeling methodologies
dc.titleCombining CNN Feature Extraction and Kolmogorov-Arnold Networks Regression for Procedural 3D Shape Generationen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
stag20251327.pdf
Size:
4.77 MB
Format:
Adobe Portable Document Format
Download
Collections
Italian Chapter Conference 2025 - Smart Tools and Apps in Graphics