🤖 AI Summary
High barriers to entry and structural integrity challenges hinder non-expert adoption of 3D procedural modeling. This paper introduces a modeling framework—integrated into Blender—that combines interpretable geometric building blocks with an extensible node graph. It defines domain-general, reusable custom geometric primitives enabling parameter-driven global and local editing while rigorously preserving shape structural validity throughout editing. The method unifies procedural shape parsing and inversion, ensuring reliable mapping from node graphs to structured 3D shapes. A user study demonstrates significant improvements in modeling accessibility and cross-domain applicability: our approach achieves higher shape inference accuracy than state-of-the-art methods, greater expressive power than coarse-grained primitive schemes, and supports fine-grained, controllable editing. The source code, dataset, procedural assets, and Blender plugin are publicly released.
📝 Abstract
The task of crafting procedural programs capable of generating structurally valid 3D shapes easily and intuitively remains an elusive goal in computer vision and graphics. Within the graphics community, generating procedural 3D models has shifted to using node graph systems. They allow the artist to create complex shapes and animations through visual programming. Being a high‐level design tool, they made procedural 3D modelling more accessible. However, crafting those node graphs demands expertise and training. We present GeoCode, a novel framework designed to extend an existing node graph system and significantly lower the bar for the creation of new procedural 3D shape programs. Our approach meticulously balances expressiveness and generalization for part‐based shapes. We propose a curated set of new geometric building blocks that are expressive and reusable across domains. We showcase three innovative and expressive programs developed through our technique and geometric building blocks. Our programs enforce intricate rules, empowering users to execute intuitive high‐level parameter edits that seamlessly propagate throughout the entire shape at a lower level while maintaining its validity. To evaluate the user‐friendliness of our geometric building blocks among non‐experts, we conduct a user study that demonstrates their ease of use and highlights their applicability across diverse domains. Empirical evidence shows the superior accuracy of GeoCode in inferring and recovering 3D shapes compared to an existing competitor. Furthermore, our method demonstrates superior expressiveness compared to alternatives that utilize coarse primitives. Notably, we illustrate the ability to execute controllable local and global shape manipulations. Our code, programs, datasets and Blender add‐on are available at https://github.com/threedle/GeoCode.
