Related papers: Linear Inverse Problems Using a Generative Compoun…
Probabilistic inversion within a multiple-point statistics framework is often computationally prohibitive for high-dimensional problems. To partly address this, we introduce and evaluate a new training-image based inversion approach for…
We present the first generative adversarial network (GAN) for natural image matting. Our novel generator network is trained to predict visually appealing alphas with the addition of the adversarial loss from the discriminator that is…
We study a new family of inverse problems for recovering representations of corrupted data. We assume access to a pre-trained representation learning network R(x) that operates on clean images, like CLIP. The problem is to recover the…
In recent years, deep neural networks have been utilized in a wide variety of applications including image generation. In particular, generative adversarial networks (GANs) are able to produce highly realistic pictures as part of tasks such…
Magnetic Resonance Imaging allows high resolution data acquisition with the downside of motion sensitivity due to relatively long acquisition times. Even during the acquisition of a single 2D slice, motion can severely corrupt the image.…
We present a learned image compression system based on GANs, operating at extremely low bitrates. Our proposed framework combines an encoder, decoder/generator and a multi-scale discriminator, which we train jointly for a generative learned…
We propose a structured prior for high-dimensional Bayesian inverse problems based on a disentangled deep generative model whose latent space is partitioned into auxiliary variables aligned with known and interpretable physical parameters…
We consider the problem of sampling from a product-of-experts-type model that encompasses many standard prior and posterior distributions commonly found in Bayesian imaging. We show that this model can be easily lifted into a novel latent…
Bayesian inference with deep generative prior has received considerable interest for solving imaging inverse problems in many scientific and engineering fields. The selection of the prior distribution is learned from, and therefore an…
The interest of the deep learning community in image synthesis has grown massively in recent years. Nowadays, deep generative methods, and especially Generative Adversarial Networks (GANs), are leading to state-of-the-art performance,…
A general framework for solving image inverse problems is introduced in this paper. The approach is based on Gaussian mixture models, estimated via a computationally efficient MAP-EM algorithm. A dual mathematical interpretation of the…
Conventional meta-atom designs rely heavily on researchers' prior knowledge and trial-and-error searches using full-wave simulations, resulting in time-consuming and inefficient processes. Inverse design methods based on optimization…
Inverse problems, i.e., estimating parameters of physical models from experimental data, are ubiquitous in science and engineering. The Bayesian formulation is the gold standard because it alleviates ill-posedness issues and quantifies…
Reliable training of generative adversarial networks (GANs) typically require massive datasets in order to model complicated distributions. However, in several applications, training samples obey invariances that are \textit{a priori}…
Deep learning techniques, especially Generative Adversarial Networks (GANs) have significantly improved image inpainting and image-to-image translation tasks over the past few years. To the best of our knowledge, the problem of combining…
Generative adversarial networks (GANs) have made great success in image inpainting yet still have difficulties tackling large missing regions. In contrast, iterative probabilistic algorithms, such as autoregressive and denoising diffusion…
Magnetic Resonance (MR) Imaging and Computed Tomography (CT) are the primary diagnostic imaging modalities quite frequently used for surgical planning and analysis. A general problem with medical imaging is that the acquisition process is…
While Generative Adversarial Networks (GANs) are fundamental to many generative modelling applications, they suffer from numerous issues. In this work, we propose a principled framework to simultaneously mitigate two fundamental issues in…
Generative Adversarial Networks (GANs) are an arrange of two neural networks -- the generator and the discriminator -- that are jointly trained to generate artificial data, such as images, from random inputs. The quality of these generated…
We introduce a novel generative autoencoder network model that learns to encode and reconstruct images with high quality and resolution, and supports smooth random sampling from the latent space of the encoder. Generative adversarial…