{"ID":3049938,"CreatedAt":"2026-06-04T02:13:16.786527022Z","UpdatedAt":"2026-06-06T15:44:26.945507316Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05068","arxiv_id":"2606.05068","title":"MaCo-GAN: Manifold-Contrastive Adversarial Learning for Single Image Super-Resolution","abstract":"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. A core component of our method is a dynamic fake sample synthesizer that transforms ground truth (GT) data into a spectrum of challenging, perceptually plausible fake images that strictly maintain low-resolution (LR) correspondence. Utilizing these synthesized samples, we establish a robust contrastive minimax game: the generator is trained to attract its predictions toward on-manifold fakes (low distortion) and repel them from off-manifold fakes (high distortion), while the discriminator optimizes the exact opposite. By simply replacing the adversarial loss of a baseline SR model with our proposed objective, we demonstrate consistent improvements in the perception-distortion trade-off across various benchmarks. Extensive ablation studies validate the effectiveness of our framework and provide deep insights into the dynamics of this conditional contrastive game.","short_abstract":"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 G...","url_abs":"https://arxiv.org/abs/2606.05068","url_pdf":"https://arxiv.org/pdf/2606.05068v1","authors":"[\"Daeyoung Han\",\"Seongmin Hwang\",\"Moongu Jeon\"]","published":"2026-06-03T16:29:44Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}