Novel Synthetic Data Tool for Data-Driven Cardboard Box Localization

Abstract

Application of neural networks in industrial settings, such as automated factories with bin-picking solutions requires costly production of large labeled data-sets. This paper presents an automatic data generation tool with a procedural model of a cardboard box. We briefly demonstrate the capabilities of the system, its various parameters and empirically prove the usefulness of the generated synthetic data by training a simple neural network. We make sample synthetic data generated by the tool publicly available.

Extended Abstract Published in 2023 Artificial Neural Networks and Machine Learning (ICANN). Published version copyrighted by Springer Nature Switzerland. Accepted: 29.6.2023. Published: 22.9.2023. This work was funded by the Horizon-Widera-2021 European Twinning project TERAIS G.A. n. 101079338. Code: https://doi.org/10.5281/zenodo.10649535 Data: https://doi.org/10.5281/zenodo.10650158

References in corpus (2)

• Synthetic 3D Data Generation Pipeline for Geometric Deep Learning in Architecture
• Towards Deep Learning-based 6D Bin Pose Estimation in 3D Scans