pgdgan
Code for the paper: Solving Linear Inverse Problems using GAN priors
view repo
In recent works, both sparsity-based methods as well as learning-based methods have proven to be successful in solving several challenging linear inverse problems. However, sparsity priors for natural signals and images suffer from poor discriminative capability, while learning-based methods seldom provide concrete theoretical guarantees. In this work, we advocate the idea of replacing hand-crafted priors, such as sparsity, with a Generative Adversarial Network (GAN) to solve linear inverse problems such as compressive sensing. In particular, we propose a projected gradient descent (PGD) algorithm for effective use of GAN priors for linear inverse problems, and also provide theoretical guarantees on the rate of convergence of this algorithm. Moreover, we show empirically that our algorithm demonstrates superior performance over an existing method of leveraging GANs for compressive sensing.
READ FULL TEXT
Deep neural networks as image priors have been recently introduced for
p...
read it
Generative priors have been shown to provide improved results over spars...
read it
While deep learning methods have achieved state-of-the-art performance i...
read it
Generative models, such as GANs, learn an explicit low-dimensional
repre...
read it
The traditional approach of hand-crafting priors (such as sparsity) for
...
read it
Trained generative models have shown remarkable performance as priors fo...
read it
A Generative Adversarial Network (GAN) with generator G trained to model...
read it
Code for the paper: Solving Linear Inverse Problems using GAN priors
Comments
There are no comments yet.