SynReconEval: Synthetic Dataset Creator for Photogrammetric Reconstruction Evaluation

Abstract

SynReconEval is an open-source framework for generating synthetic datasets to benchmark photogrammetric and neural 3D reconstruction methods. It leverages Blender to render controlled RGB, depth, and normal maps with full camera metadata, which are then processed by reconstruction pipelines. The reconstructed models are evaluated against ground-truth geometry using a wide range of metrics, including precision, recall, and spatial error distributions. The system’s modular design allows easy integration of new renderers, algorithms, and evaluation criteria, enabling large-scale, reproducible, and customizable assessment of reconstruction performance.

Keywords: photogrammetry, synthetic dataset generation, reconstruction evaluation