Solving Inverse Problems with Conditional-GAN Prior via Fast Network-Projected Gradient Descent

TL;DR

This paper introduces a fast network-based projected gradient descent (NPGD) method combined with conditional BEGAN to efficiently solve inverse problems like compressed sensing, achieving significant speed-ups and high-quality reconstructions.

Contribution

It proposes a novel NPGD algorithm integrated with conditional BEGAN for faster inverse problem solving using generative models.

Findings

NPGD with conditional BEGAN achieves up to 175 times faster reconstruction.

The method maintains or improves reconstruction quality compared to traditional approaches.

Experiments on MNIST and CelebA datasets validate the effectiveness of the approach.

Abstract

The projected gradient descent (PGD) method has shown to be effective in recovering compressed signals described in a data-driven way by a generative model, i.e., a generator which has learned the data distribution. Further reconstruction improvements for such inverse problems can be achieved by conditioning the generator on the measurement. The boundary equilibrium generative adversarial network (BEGAN) implements an equilibrium based loss function and an auto-encoding discriminator to better balance the performance of the generator and the discriminator. In this work we investigate a network-based projected gradient descent (NPGD) algorithm for measurement-conditional generative models to solve the inverse problem much faster than regular PGD. We combine the NPGD with conditional GAN/BEGAN to evaluate their effectiveness in solving compressed sensing type problems. Our experiments on the MNIST and CelebA datasets show that the combination of measurement conditional model with NPGD works well in recovering the compressed signal while achieving similar or in some cases even better performance along with a much faster reconstruction. The achieved reconstruction speed-up in our experiments is up to 140-175.