English

Learning Latent Representations for Image Translation using Frequency Distributed CycleGAN

Computer Vision and Pattern Recognition 2025-08-06 v1 Artificial Intelligence Graphics

Abstract

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. To 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.

Keywords

Cite

@article{arxiv.2508.03415,
  title  = {Learning Latent Representations for Image Translation using Frequency Distributed CycleGAN},
  author = {Shivangi Nigam and Adarsh Prasad Behera and Shekhar Verma and P. Nagabhushan},
  journal= {arXiv preprint arXiv:2508.03415},
  year   = {2025}
}

Comments

This paper is currently under review for publication in an IEEE Transactions. If accepted, the copyright will be transferred to IEEE

R2 v1 2026-07-01T04:35:07.601Z