Full-Glow: Fully conditional Glow for more realistic image generation
This work addresses the problem of generating realistic synthetic training data for autonomous agents, such as driverless cars, to reduce the need for extensive manual labeling.
The authors developed Full-Glow, a conditional generative model that creates realistic street scenes from semantic segmentation maps. Their model outperforms recent works in terms of the semantic segmentation performance of a pretrained PSPNet, indicating higher realism and suitability for training visual recognition systems.
Autonomous agents, such as driverless cars, require large amounts of labeled visual data for their training. A viable approach for acquiring such data is training a generative model with collected real data, and then augmenting the collected real dataset with synthetic images from the model, generated with control of the scene layout and ground truth labeling. In this paper we propose Full-Glow, a fully conditional Glow-based architecture for generating plausible and realistic images of novel street scenes given a semantic segmentation map indicating the scene layout. Benchmark comparisons show our model to outperform recent works in terms of the semantic segmentation performance of a pretrained PSPNet. This indicates that images from our model are, to a higher degree than from other models, similar to real images of the same kinds of scenes and objects, making them suitable as training data for a visual semantic segmentation or object recognition system.