Self-Attending Task Generative Adversarial Network for Realistic Satellite Image Creation
This work addresses the challenge of generating realistic satellite imagery for space observation applications, representing an incremental improvement in domain-specific data augmentation.
The authors tackled the problem of augmenting synthetic satellite images with realistic noise and sensor characteristics while preserving semantic content, achieving a reduction in hallucinatory objects and obfuscation in space observation scenes.
We introduce a self-attending task generative adversarial network (SATGAN) and apply it to the problem of augmenting synthetic high contrast scientific imagery of resident space objects with realistic noise patterns and sensor characteristics learned from collected data. Augmenting these synthetic data is challenging due to the highly localized nature of semantic content in the data that must be preserved. Real collected images are used to train a network what a given class of sensor's images should look like. The trained network then acts as a filter on noiseless context images and outputs realistic-looking fakes with semantic content unaltered. The architecture is inspired by conditional GANs but is modified to include a task network that preserves semantic information through augmentation. Additionally, the architecture is shown to reduce instances of hallucinatory objects or obfuscation of semantic content in context images representing space observation scenes.