mlsanityData to 14 Oct 2026

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

arXiv 2604.26943 ↗First posted 29 Apr 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 55 references that are in the map. First posted on arXiv 29 Apr 2026.

Builds on

29 of 55 references.

References · 29

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  3. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 380
  4. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 353
  5. 2023LayoutGPT: Compositional Visual Planning and Generation with Large Language Modelscited by 347
  6. 2023Holodeck: Language Guided Generation of 3D Embodied AI Environmentscited by 268
  7. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 173
  8. 2023Infinite Photorealistic Worlds using Procedural Generationcited by 147
  9. 2024Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generationcited by 137
  10. 2024LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Modelscited by 96
  11. 20233D-GPT: Procedural 3D Modeling with Large Language Modelscited by 95
  12. 2025SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agentcited by 56
17 more
  1. 2024The Scene Language: Representing Scenes with Programs, Words, and Embeddingscited by 36
  2. 2025BlenderGym: Benchmarking Foundational Model Systems for Graphics Editingcited by 31
  3. 2025FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placementcited by 25
  4. 2024BlenderAlchemy: Editing 3D Graphics with Vision-Language Modelscited by 22
  5. 2025WorldCraft: Photo-Realistic 3D World Creation and Customization via LLM Agentscited by 21
  6. 2026Code2Worlds: Empowering Coding LLMs for 4D World Generationcited by 19
  7. 2025Procedural Scene Programs for Open-Universe Scene Generation: LLM-Free Error Correction via Program Searchcited by 10
  8. 2025VLMaterial: Procedural Material Generation with Large Vision-Language Modelscited by 9
  9. 2025RoomCraft: Controllable and Complete 3D Indoor Scene Generationcited by 9
  10. 2025Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimationcited by 8
  11. 2025What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?cited by 7
  12. 2024ParSEL: Parameterized Shape Editing with Languagecited by 6
  13. 2024Arti-PG: A Toolbox for Procedurally Synthesizing Large-Scale and Diverse Articulated Objects with Rich Annotationscited by 6
  14. 2025ShapeLib: Designing a library of programmatic 3D shape abstractions with Large Language Modelscited by 5
  15. 2025InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexitycited by 5
  16. 2025Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbationscited by 4
  17. 2025Synthesizing 3D Abstractions by Inverting Procedural Buildings with Transformerscited by 1

Built on by

Not cited yet.