Synthetic-to-real data translation using generative adversarial learning has achieved significant success in improving synthetic data. Yet, limited studies focus on deep evaluation and comparison of adversarial training on general-purpose synthetic data for machine learning. This work aims to train and evaluate a synthetic-to-real generative model that transforms the synthetic renderings into more realistic styles on general-purpose datasets conditioned with unlabeled real-world data. Extensive performance evaluation and comparison have been conducted through qualitative and quantitative metrics and a defined downstream perception task.
@article{arxiv.2304.12463,
title = {A Study on Improving Realism of Synthetic Data for Machine Learning},
author = {Tingwei Shen and Ganning Zhao and Suya You},
journal= {arXiv preprint arXiv:2304.12463},
year = {2023}
}
Comments
8 pages, 1 figure, 7 tables. Submit to the "SPIE Defense + Commercial Sensing" conference