Towards synthetic generation of realistic wooden logs

2025-03-18

AI Summary

Sawmills lack in-situ annotated data on internal knot distributions within logs, hindering the development of robust knot prediction and intelligent sawing systems. Current approaches rely heavily on costly, low-throughput CT scanning for ground-truth internal structure labeling. Method: This paper proposes a CT-free 3D log synthesis method integrating biologically informed tree growth modeling with CT-data-driven parameter fitting. It jointly generates realistic 3D knot growth trajectories and corresponding surface-penetrating regions for the first time, while enforcing physical consistency between internal and external structures via unified geometric-topological modeling. Contribution/Results: The synthesized digital twin log models achieve high fidelity against real CT scans, enabling scalable, high-fidelity synthetic dataset generation. This approach provides a reliable, cost-effective data foundation for training knot prediction models and intelligent sawing systems, effectively alleviating the bottleneck of CT-dependent internal structure annotation.

Technology Category

• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Search and Optimization: Sampling/Simulation-based Search
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

In this work, we propose a novel method to synthetically generate realistic 3D representations of wooden logs. Efficient sawmilling heavily relies on accurate measurement of logs and the distribution of knots inside them. Computed Tomography (CT) can be used to obtain accurate information about the knots but is often not feasible in a sawmill environment. A promising alternative is to utilize surface measurements and machine learning techniques to predict the inner structure of the logs. However, obtaining enough training data remains a challenge. We focus mainly on two aspects of log generation: the modeling of knot growth inside the tree, and the realistic synthesis of the surface including the regions, where the knots reach the surface. This results in the first log synthesis approach capable of generating both the internal knot and external surface structures of wood. We demonstrate that the proposed mathematical log model accurately fits to real data obtained from CT scans and enables the generation of realistic logs.

Problem

• Synthetic generation of realistic 3D wooden logs
• Predicting internal knot distribution using surface measurements
• Modeling knot growth and realistic surface synthesis

Innovation

• Synthetic 3D wooden log generation using machine learning
• Modeling internal knot growth and external surface synthesis
• Mathematical log model validated with CT scan data