A Study on Improving Realism of Synthetic Data for Machine Learning

Synthetic-to-real data translation using generative adversarial learning has achieved significant success to improve synthetic data. Yet, there are limited studies focusing 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.