ProcFunc: Function-Oriented Abstractions for Procedural 3D Generation in Python

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Raistrick, Alexander, Kayan, Karhan, Nugent, Jack, Yan, David, Mei, Lingjie, Parakh, Meenal, Wen, Hongyu, Li, Dylan, Zuo, Yiming, Liang, Erich, Deng, Jia
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915967869648896
author Raistrick, Alexander
Kayan, Karhan
Nugent, Jack
Yan, David
Mei, Lingjie
Parakh, Meenal
Wen, Hongyu
Li, Dylan
Zuo, Yiming
Liang, Erich
Deng, Jia
author_facet Raistrick, Alexander
Kayan, Karhan
Nugent, Jack
Yan, David
Mei, Lingjie
Parakh, Meenal
Wen, Hongyu
Li, Dylan
Zuo, Yiming
Liang, Erich
Deng, Jia
contents We introduce ProcFunc, a library for Blender-based procedural 3D generation in Python. ProcFunc provides a library of easy-to-use Python functions, which streamline creating, combining, analyzing, and executing procedural generation code. ProcFunc makes it easy to create large-scale diverse training data, by combinatorial compositions of semantic components. VLMs can use ProcFunc to edit procedural material and geometry code and can create new procedural code with significantly fewer coding errors. Finally, as an example use case, we use ProcFunc to develop a new procedural generator of indoor rooms, which includes a collection of new compositional procedural materials. We demonstrate the detail, runtime efficiency, and diversity of this room generator, as well as its use for 3D synthetic data generation. Please visit https://github.com/princeton-vl/procfunc for source code.
format Preprint
id arxiv_https___arxiv_org_abs_2604_26943
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ProcFunc: Function-Oriented Abstractions for Procedural 3D Generation in Python
Raistrick, Alexander
Kayan, Karhan
Nugent, Jack
Yan, David
Mei, Lingjie
Parakh, Meenal
Wen, Hongyu
Li, Dylan
Zuo, Yiming
Liang, Erich
Deng, Jia
Computer Vision and Pattern Recognition
We introduce ProcFunc, a library for Blender-based procedural 3D generation in Python. ProcFunc provides a library of easy-to-use Python functions, which streamline creating, combining, analyzing, and executing procedural generation code. ProcFunc makes it easy to create large-scale diverse training data, by combinatorial compositions of semantic components. VLMs can use ProcFunc to edit procedural material and geometry code and can create new procedural code with significantly fewer coding errors. Finally, as an example use case, we use ProcFunc to develop a new procedural generator of indoor rooms, which includes a collection of new compositional procedural materials. We demonstrate the detail, runtime efficiency, and diversity of this room generator, as well as its use for 3D synthetic data generation. Please visit https://github.com/princeton-vl/procfunc for source code.
title ProcFunc: Function-Oriented Abstractions for Procedural 3D Generation in Python
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.26943