From Words to Wood: Text‐to‐Procedurally Generated Wood Materials
Advanced procedural generation of wood materials with natural language interface
Project Overview
In the domain of wood modeling, we present a new complex appearance model, coupled with a user‐friendly NLP‐based frontend for intuitive interactivity. First, we present a procedurally generated wood model that is capable of accurately simulating intricate wood characteristics, including growth rings, vessels/pores, rays, knots, and figure. Furthermore, newly developed features were introduced, including brushiness distortion, influence points, and individual feature control. These novel enhancements facilitate a more precise matching between procedurally generated wood and ground truth images. Second, we present a text‐based user interface that relies on a trained natural language processing model that is designed to map user plain English requests into the parameter space of our procedurally generated wood model. This significantly reduces the complexity of the authoring process, thereby enabling any user, regardless of their level of woodworking expertise or familiarity with procedurally generated materials, to utilize it to its fullest potential.
Key Features
- State-of-the-art procedurally generated wood features, plus newly introduced ones
- Natural-language (NLP) interface
- Dataset with more than 497 wood configurations
- PBR texture generation from any input mesh
Technical Implementation
The system utilizes advanced procedural generation algorithms to create authentic wood patterns. The natural language interface employs machine learning techniques to parse user descriptions and map them to appropriate material parameters. This creates a bridge between artistic intent and technical implementation, making the tool accessible to both technical artists and designers without deep technical knowledge.
Comparative analysis of microscopic images of various pore distributions with rendered diagrams generated by our procedurally generated wood model through the use of piecewise linear functions.
Visual Results
.png)
Pine wood material with natural grain patterns
Detailed wood knot formation
Complex knot structure simulation
.png)
Ash wood with distinctive grain
.png)
Tree trunk cross-section with growth rings
Project teaser showcasing capabilities
Animation Demo
High-resolution animation demonstrating the material system in action
Applications & Impact
This research has significant implications for the gaming and entertainment industries, where realistic materials are crucial for immersive experiences. The system's ability to generate game-ready assets from any input mesh makes it particularly valuable for game developers and 3D artists. The natural language interface democratizes access to advanced material creation, allowing creative professionals to focus on artistic vision rather than technical implementation.
Acknowledgement
We express our sincere appreciation to Martin Mirbauer for his extensive support throughout the project and to Ali Ahmed Maher Dali for his expert assistance in data processing. This work received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement No 956585, and from the Czech Science Foundation (GAČR) grant No. 22-22875S, which we gratefully acknowledge. The work was supported by the grant SVV-2025-260822. Open access publishing facilitated by Univerzita Karlova, as part of the Wiley – CzechELib agreement.