Image-based model parameter optimisation using Model-Assisted Generative Adversarial Networks

11/30/2018
by   Saúl Alonso-Monsalve, et al.
0

We propose and demonstrate the use of a Model-Assisted Generative Adversarial Network to produce simulated images that accurately match true images through the variation of underlying model parameters that describe the image generation process. The generator learns the parameter values that give images that best match the true images. Two case studies show the excellent agreement between the generated best match parameters and the true parameters. The best match parameter values that produce the most accurate simulated images can be extracted and used to re-tune the default simulation to minimise any bias when applying image recognition techniques to simulated and true images. In the case of a real-world experiment, the true data is replaced by experimental data with unknown true parameter values. The Model-Assisted Generative Adversarial Network uses a convolutional neural network to emulate the simulation for all parameter values that, when trained, can be used as a conditional generator for fast image production.

READ FULL TEXT

page 4

page 5

research
07/19/2016

Generating Images Part by Part with Composite Generative Adversarial Networks

Image generation remains a fundamental problem in artificial intelligenc...
research
06/19/2023

Probabilistic matching of real and generated data statistics in generative adversarial networks

Generative adversarial networks constitute a powerful approach to genera...
research
11/28/2022

Using a Conditional Generative Adversarial Network to Control the Statistical Characteristics of Generated Images for IACT Data Analysis

Generative adversarial networks are a promising tool for image generatio...
research
01/13/2019

Introducing a Generative Adversarial Network Model for Lagrangian Trajectory Simulation

We introduce a generative adversarial network (GAN) model to simulate th...
research
07/26/2018

AlphaGAN: Generative adversarial networks for natural image matting

We present the first generative adversarial network (GAN) for natural im...
research
10/13/2021

Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks

A central task of a Disc Jockey (DJ) is to create a mixset of mu-sic wit...
research
08/16/2017

Efficient training-image based geostatistical simulation and inversion using a spatial generative adversarial neural network

Probabilistic inversion within a multiple-point statistics framework is ...

Please sign up or login with your details

Forgot password? Click here to reset