AI RESEARCH
MaCo-GAN: Manifold-Contrastive Adversarial Learning for Single Image Super-Resolution
arXiv CS.CV
•
ArXi:2606.05068v1 Announce Type: new Conventional Generative Adversarial Networks (GANs) for Single Image Super-Resolution (SISR) often struggle with hallucinated artifacts, largely because standard discriminators evaluate overall image naturalness rather than strict conditional realism. To address this, we propose MaCo-GAN, a novel manifold-contrastive GAN framework that replaces the conventional adversarial loss with a supervised contrastive objective.