vix.ing · top · new · best · stats · spec

Quality Aware Generative Adversarial Networks

2019/11/08 by Parimala Kancharla, Kancharla, Parimala, Sumohana S. Channappayya +1 · 2 citations
Computer Science · #Advanced Image Processing Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Signal Denoising Methods #Image and Video Processing (eess.IV) #Image and Video Quality Assessment #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.1911.03149

openalex created_date 2019/09/05 · openalex publication_date 2019/11/08 · openalex updated_date 2026/07/28

Abstract

Generative Adversarial Networks (GANs) have become a very popular tool for implicitly learning high-dimensional probability distributions. Several improvements have been made to the original GAN formulation to address some of its shortcomings like mode collapse, convergence issues, entanglement, poor visual quality etc. While a significant effort has been directed towards improving the visual quality of images generated by GANs, it is rather surprising that objective image quality metrics have neither been employed as cost functions nor as regularizers in GAN objective functions. In this work, we show how a distance metric that is a variant of the Structural SIMilarity (SSIM) index (a popular full-reference image quality assessment algorithm), and a novel quality aware discriminator gradient penalty function that is inspired by the Natural Image Quality Evaluator (NIQE, a popular no-reference image quality assessment algorithm) can each be used as excellent regularizers for GAN objective functions. Specifically, we demonstrate state-of-the-art performance using the Wasserstein GAN gradient penalty (WGAN-GP) framework over CIFAR-10, STL10 and CelebA datasets.

Cited by

Related