A Study on NeRF-based Synthetic Image Generation and Post-processing Method for Object Detection

Recently, the importance of securing data in the field of computer vision using machine learning is increasing. In this situation, research to use synthetic images as training data in fields where real images cannot be used for various reasons is ongoing. In particular, in the defense field, where it is difficult to know the characteristics of imaging devices, neural network learning using synthetic images is essential for the introduction of civilian technology. In this paper, we propose a method to use for object detection neural network training by generating synthetic images instead of real images and removing artifacts from the generated images.