Generative Imaging and Image Processing via Generative Encoder

This paper introduces a novel generative encoder (GE) model for generative imaging and image processing with applications in compressed sensing and imaging, image compression, denoising, inpainting, deblurring, and super-resolution. The GE model consists of a pre-training phase and a solving phase. In the pre-training phase, we separately train two deep neural networks: a generative adversarial network (GAN) with a generator that captures the data distribution of a given image set, and an auto-encoder (AE) network with an encoder that compresses images following the estimated distribution by GAN. In the solving phase, given a noisy image , where is the target unknown image, is an operator adding an addictive, or multiplicative, or convolutional noise, or equivalently given such an image in the compressed domain, i.e., given , we solve the optimization problem \[ z^*=\underset{z}{\mathrm{argmin}} \|\EN(\G(z))-m\|_2^2+\lambda\|z\|_2^2 \] to recover the image in a generative way via , where is a hyperparameter. The GE model unifies the generative capacity of GANs and the stability of AEs in an optimization framework above instead of stacking GANs and AEs into a single network or combining their loss functions into one as in existing literature. Numerical experiments show that the proposed model outperforms several state-of-the-art algorithms.
View on arXiv