FloraForge: LLM-Assisted Procedural Generation of Editable and Analysis-Ready 3D Plant Geometric Models For Agricultural Applications

2025-12-11

AI Summary

Existing approaches struggle to simultaneously satisfy the divergent requirements of agricultural computational phenotyping and physical simulation for 3D plant modeling: learning-based methods rely heavily on large-scale annotated data and yield non-editable outputs, whereas procedural modeling demands prohibitively high expertise. This paper introduces the first LLM-augmented parametric plant modeling framework, enabling domain experts to generate editable, analysis-ready 3D plant models via natural-language interaction (“Plant Refinements”). The framework automatically compiles textual plant descriptions into hierarchical B-spline surface representations compliant with botanical constraints, integrating LLM-driven semantic understanding, parametric procedural modeling, point-cloud fitting, and explicit control-point–driven deformation. Evaluated on maize, soybean, and mung bean, the framework produces high-fidelity triangular meshes and parameter-rich, analysis-ready grids—seamlessly supporting downstream multi-physics tasks including light transport simulation, computational fluid dynamics (CFD), and finite element analysis (FEA).

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Accurate 3D plant models are crucial for computational phenotyping and physics-based simulation; however, current approaches face significant limitations. Learning-based reconstruction methods require extensive species-specific training data and lack editability. Procedural modeling offers parametric control but demands specialized expertise in geometric modeling and an in-depth understanding of complex procedural rules, making it inaccessible to domain scientists. We present FloraForge, an LLM-assisted framework that enables domain experts to generate biologically accurate, fully parametric 3D plant models through iterative natural language Plant Refinements (PR), minimizing programming expertise. Our framework leverages LLM-enabled co-design to refine Python scripts that generate parameterized plant geometries as hierarchical B-spline surface representations with botanical constraints with explicit control points and parametric deformation functions. This representation can be easily tessellated into polygonal meshes with arbitrary precision, ensuring compatibility with functional structural plant analysis workflows such as light simulation, computational fluid dynamics, and finite element analysis. We demonstrate the framework on maize, soybean, and mung bean, fitting procedural models to empirical point cloud data through manual refinement of the Plant Descriptor (PD), human-readable files. The pipeline generates dual outputs: triangular meshes for visualization and triangular meshes with additional parametric metadata for quantitative analysis. This approach uniquely combines LLM-assisted template creation, mathematically continuous representations enabling both phenotyping and rendering, and direct parametric control through PD. The framework democratizes sophisticated geometric modeling for plant science while maintaining mathematical rigor.

Problem

• Generates editable 3D plant models via natural language for agricultural applications.
• Overcomes limitations of data-intensive learning and expert-dependent procedural modeling.
• Enables parametric plant geometry creation compatible with scientific analysis workflows.

Innovation

• LLM-assisted natural language procedural modeling
• Hierarchical B-spline surface with botanical constraints
• Dual-output meshes for visualization and analysis