Approximating Procedural Models of 3D Shapes with Neural Networks
Loading...
Date
2025
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
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.
Description
CCS Concepts: Computing methodologies → Computer graphics; Shape modeling
@article{10.1111:cgf.70024,
journal = {Computer Graphics Forum},
title = {{Approximating Procedural Models of 3D Shapes with Neural Networks}},
author = {Hossain, Ishtiaque and Shen, I-Chao and Kaick, Oliver van},
year = {2025},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.70024}
}