AmbientGAN: Generative models from lossy measurements

By Ashish Bora, Eric Price, A. Dimakis. 2018

223 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Generative Models

Citations in the corpus

Training Generative Adversarial Networks with Limited Data (2020, background): “[4] consider a similar problem in training GANs under corrupted measurements, and show that the training implicitly undoes the corruptions and finds the correct distribution, as long as the corruption process is represented by an invertible transformation of probability distributions over the data s”
PacGAN: The Power of Two Samples in Generative Adversarial Networks (2017, neutral): “, [41], [42]).”
Deep Learning Techniques for Inverse Problems in Imaging (2020, methodology): “We will discuss how DGMs can be used as priors for inverse problems [25, 76, 77].”
Robust Compressed Sensing MRI with Deep Generative Priors (2021, background): “Further, [17] studies the harder problem of learning a generative model for a class of images using only partial observations, as first proposed in AmbientGAN [14].”
Multivariate Time Series Imputation with Generative Adversarial Networks (2018, methodology): “GAN is also successfully used to complete faces [5, 30, 33, 31].”
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications (2020, background): “Because GANs have become popular throughout the deep learning area, its limitations have recently been improved [446], [447].”
Image-Adaptive GAN based Reconstruction (2019, unknown): “This shortcoming is mainly due to the limited representation capabilities of the generative models (see Section 6.3 in (Bora et al. 2017)), and is common to related recent works (Hand, Leong, and Voroninski 2018; Bora, Price, and Dimakis 2018; Dhar, Grover, and Ermon 2018; Shah and Hegde 2018).”
pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis (2020, background): “Generative Adversarial Nets (GANs) [15], or more generally the paradigm of adversarial learning, have led to significant progress in various image synthesis tasks, including image generation [49, 24, 25, 26], image-to-image translation [68], interactive image editing [63], and learning from partial ”