SPatchGAN: A Statistical Feature Based Discriminator for Unsupervised Image-to-Image Translation
Xuning Shao, Weidong Zhang
Abstract
For unsupervised image-to-image translation, we propose a discriminator architecture which focuses on the statistical features instead of individual patches. The network is stabilized by distribution matching of key statistical features at multiple scales. Unlike the existing methods which impose more and more constraints on the generator, our method facilitates the shape deformation and enhances the fine details with a greatly simplified framework. We show that the proposed method outperforms the existing state-of-the-art models in various challenging applications including selfie-to-anime, male-to-female and glasses removal.
Topics & Concepts
DiscriminatorComputer scienceArtificial intelligenceImage (mathematics)Generator (circuit theory)Translation (biology)Feature (linguistics)Pattern recognition (psychology)Image translationKey (lock)Feature extractionMatching (statistics)Computer visionStatistical modelPower (physics)MathematicsStatisticsDetectorLinguisticsMessenger RNAQuantum mechanicsChemistryTelecommunicationsPhilosophyPhysicsBiochemistryComputer securityGeneGenerative Adversarial Networks and Image SynthesisVideo Analysis and SummarizationDigital Media Forensic Detection