Simplified one-sided Image-to-Image Translation with Reconstruction-Constrained Generative Adversarial Networks

The utilization of generative adversarial networks (GANs) for image-to-image translation has undergone extensive scholarly exploration. Nonetheless, prevailing unidirectional image translation tasks remain intricate and computationally inefficient due to the employment of complex computational methods and supplementary network modules, thereby imposing a significant computational burden. This study suggests integrating reconstruction constraints as a surrogate for complex ones, reducing computational burden. By skillfully combining these with adversarial losses, the network performs image translation more effectively. To enhance both translational and reconstruction competencies, we propose using the discriminator’s encoding mechanism to retain the image’s attributes. This approach results in a simplified yet powerful unidirectional image translation model, proven superior through comparative analysis with various GAN-based models. Additionally, the practical efficacy of our model is empirically verified through systematic experimentation.