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

no code implementations • 2 Sep 2021 • Muhammad Fadli Damara, Gregor Kornhardt, Peter Jung

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.

Generative Adversarial Network