Quality Aware Generative Adversarial Networks
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.
Code (1)
Tasks
Full reference image quality assessmentFull-Reference Image Quality AssessmentImage GenerationImage Quality AssessmentNo-Reference Image Quality AssessmentSSIMMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
We have witnessed rapid progress on 3D-aware image synthesis, leveraging recent advances in generative visual models and neural rendering. Existing approaches however fall short in two ways: first, they may lack an under…
3D-Aware Image SynthesisImage GenerationNeural RenderingScene GenerationGAGAN: Geometry-Aware Generative Adversarial Networks
Deep generative models learned through adversarial training have become increasingly popular for their ability to generate naturalistic image textures. However, aside from their texture, the visual appearance of objects …
Face GenerationImage GenerationLearning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
We provide a bridge between generative modeling in the Machine Learning community and simulated physical processes in High Energy Particle Physics by applying a novel Generative Adversarial Network (GAN) architecture to …
Generative Adversarial NetworkMulti-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis
3D-aware image synthesis aims to generate images of objects from multiple views by learning a 3D representation. However, one key challenge remains: existing approaches lack geometry constraints, hence usually fail to ge…
3D-Aware Image Synthesis3D geometryImage Generation3D-Aware Video Generation
Generative models have emerged as an essential building block for many image synthesis and editing tasks. Recent advances in this field have also enabled high-quality 3D or video content to be generated that exhibits eit…
Image GenerationVideo Generation