Computer vision for real-world applications faces data acquisition challenges, including accessibility, high costs, difficulty in obtaining diversity in scenarios or environmental conditions. Synthetic data usage has surged as a solution to these obstacles. Leveraging game engines for synthetic dataset creation effectively enriches training datasets with increased diversity and richness. The choice of the game engine, pivotal for generating photorealistic simulations, may influence synthetic data quality. This study compares Unity Engine’s and Unreal Engine’s capabilities in generating synthetic maritime datasets to support ship recognition applications. To this end, the realworld maritime dataset ShipSG has been replicated in the corresponding game engines to create the same scenarios. The performance of the generated synthetic datasets is benchmarked against the real-world ShipSG dataset using the object recognition model YOLOv8. Furthermore, the comparison evaluates various photorealistic parameters found in the dataset images to determine the optimal configuration for improving performance with YOLOv8. The datasets generated using the Unity Engine, with all photorealistic effects present and the one with no lens distortion, achieved the highest accuracy in ship recognition with a mAP of 72.3%. Both configurations of the synthetic datasets were utilised to augment the ShipSG dataset to train YOLOv8. The configuration with all photorealistic parameters in place provides the highest mAP increase, of 0.4% compared with YOLOv8 performance on ShipSG when no synthetic data is used. This evidence underscores that utilising game engines can effectively support and enhance ship recognition tasks