Self-Attending Task Generative Adversarial Network for Realistic Satellite Image Creation

11/18/2021
by   Nathan Toner, et al.
3

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.

READ FULL TEXT

page 1

page 2

page 4

page 5

page 6

page 7

page 8

page 9

research
08/01/2017

Deep Generative Adversarial Neural Networks for Realistic Prostate Lesion MRI Synthesis

Generative Adversarial Neural Networks (GANs) are applied to the synthet...
research
07/22/2023

Synthesis of Batik Motifs using a Diffusion – Generative Adversarial Network

Batik, a unique blend of art and craftsmanship, is a distinct artistic a...
research
06/03/2020

From Real to Synthetic and Back: Synthesizing Training Data for Multi-Person Scene Understanding

We present a method for synthesizing naturally looking images of multipl...
research
05/03/2022

Splicing Detection and Localization In Satellite Imagery Using Conditional GANs

The widespread availability of image editing tools and improvements in i...
research
02/19/2019

Using Conditional Generative Adversarial Networks to Generate Ground-Level Views From Overhead Imagery

This paper develops a deep-learning framework to synthesize a ground-lev...
research
07/29/2022

Image Augmentation for Satellite Images

This study proposes the use of generative models (GANs) for augmenting t...
research
01/16/2021

GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving

Scalable sensor simulation is an important yet challenging open problem ...

Please sign up or login with your details

Forgot password? Click here to reset