Learning Latent Representations for Image Translation using Frequency Distributed CycleGAN

--This paper presents Fd-CycleGAN, an image-to-image (I2I) translation framework that enhances latent representation learning to approximate real data distributions. Building upon the foundation of CycleGAN, our approach integrates Local Neighborhood Encoding (LNE) and Frequency-aware supervision to capture fine-grained local pixel semantics while preserving structural coherence from the source domain. We employ distribution-based loss metrics, including KL/JS Divergence and log-based similarity measures, to explicitly quantify the alignment between real and generated image distributions in both spatial and frequency domains. T o validate the efficacy of Fd-CycleGAN, we conduct experiments on diverse datasets--Horse2Zebra, Monet2Photo, and a synthetically augmented Strike-off dataset. Compared to baseline CycleGAN and other state-of-the-art methods, our approach demonstrates superior perceptual quality, faster convergence, and improved mode diversity, particularly in low-data regimes. By effectively capturing local and global distribution characteristics, Fd-CycleGAN achieves more visually coherent and semantically consistent translations. Our results suggest that frequency-guided latent learning significantly improves generalization in image translation tasks, with promising applications in document restoration, artistic style transfer, and medical image synthesis. We also provide comparative insights with diffusion-based generative models, highlighting the advantages of our lightweight adversarial approach in terms of training efficiency and qualitative output. Domain Translation (DT), also referred to as I2I translation, involves learning a mapping between two visual domains, often in the absence of paired data. This task has become central to several vision tasks. For these tasks, generative models have been widely adopted [1]-[3].