# Advancing the AmbientGAN for learning stochastic object models

arXiv: https://arxiv.org/abs/2102.00281 · HTML: https://mlsanity.com/paper/2102.00281/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 15 references that are in the map.
- First posted on arXiv 30 Jan 2021.

## Builds on (most cited first, 11 of 11)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Compressible Latent-Space Invertible Networks for Generative Model-Constrained Image Reconstruction](https://mlsanity.com/paper/2007.02462/) (2020)
- [Approximating the Ideal Observer and Hotelling Observer for binary signal detection tasks by use of supervised learning methods](https://mlsanity.com/paper/1905.06330/) (2019)
- [Medical image reconstruction with image-adaptive priors learned by use of generative adversarial networks](https://mlsanity.com/paper/2001.10830/) (2020)
- [Approximating the Ideal Observer for joint signal detection and localization tasks by use of supervised learning methods](https://mlsanity.com/paper/2006.00112/) (2020)
- [Markov-Chain Monte Carlo Approximation of the Ideal Observer using Generative Adversarial Networks](https://mlsanity.com/paper/2001.09526/) (2020)
- [Feeding the zombies: Synthesizing brain volumes using a 3D progressive growing GAN](https://mlsanity.com/paper/1912.05357/) (2019)
- [Learning stochastic object models from medical imaging measurements using Progressively-Growing AmbientGANs](https://mlsanity.com/paper/2006.00033/) (2020)
- [Progressively-Growing AmbientGANs For Learning Stochastic Object Models From Imaging Measurements](https://mlsanity.com/paper/2001.09523/) (2020)

## Built on by (most cited first, 2 of 2)

- [Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networks](https://mlsanity.com/paper/2106.14324/) (2021)
- [Ideal Observer Computation by Use of Markov-Chain Monte Carlo with Generative Adversarial Networks](https://mlsanity.com/paper/2304.00433/) (2023)

## Abstract (arXiv)

Medical imaging systems are commonly assessed and optimized by use of objective-measures of image quality (IQ) that quantify the performance of an observer at specific tasks. Variation in the objects to-be-imaged is an important source of variability that can significantly limit observer performance. This object variability can be described by stochastic object models (SOMs). In order to establish SOMs that can accurately model realistic object variability, it is desirable to use experimental data. To achieve this, an augmented generative adversarial network (GAN) architecture called AmbientGAN has been developed and investigated. However, AmbientGANs cannot be immediately trained by use of advanced GAN training methods such as the progressive growing of GANs (ProGANs). Therefore, the ability of AmbientGANs to establish realistic object models is limited. To circumvent this, a progressively-growing AmbientGAN (ProAmGAN) has been proposed. However, ProAmGANs are designed for generating two-dimensional (2D) images while medical imaging modalities are commonly employed for imaging three-dimensional (3D) objects. Moreover, ProAmGANs that employ traditional generator architectures lack the ability to control specific image features such as fine-scale textures that are frequently considered when optimizing imaging systems. In this study, we address these limitations by proposing two advanced AmbientGAN architectures: 3D ProAmGANs and Style-AmbientGANs (StyAmGANs). Stylized numerical studies involving magnetic resonance (MR) imaging systems are conducted. The ability of 3D ProAmGANs to learn 3D SOMs from imaging measurements and the ability of StyAmGANs to control fine-scale textures of synthesized objects are demonstrated.