Advancing Digital Twin Generation Through a Novel Simulation Framework and Quantitative Benchmarking
This work addresses the need for quantitative benchmarking in digital twin generation, which is incremental as it builds on existing photogrammetry methods by adding a simulation framework for better evaluation.
The paper tackled the problem of generating 3D models from real-world objects by developing a novel pipeline for creating synthetic images from high-quality 3D models and programmatically generated camera poses, enabling repeatable and quantifiable experiments to compare ground-truth parameters against reconstructed estimations.
The generation of 3D models from real-world objects has often been accomplished through photogrammetry, i.e., by taking 2D photos from a variety of perspectives and then triangulating matched point-based features to create a textured mesh. Many design choices exist within this framework for the generation of digital twins, and differences between such approaches are largely judged qualitatively. Here, we present and test a novel pipeline for generating synthetic images from high-quality 3D models and programmatically generated camera poses. This enables a wide variety of repeatable, quantifiable experiments which can compare ground-truth knowledge of virtual camera parameters and of virtual objects against the reconstructed estimations of those perspectives and subjects.