Paired and Unpaired Image to Image Translation using Generative Adversarial Networks
This work addresses image style and domain translation for computer vision applications, but it appears incremental as it builds on existing GAN methods without introducing major innovations.
The paper tackled image-to-image translation using GANs for both paired and unpaired tasks, achieving results analyzed with metrics like FID score, precision, and recall, though no specific numerical improvements were reported.
Image to image translation is an active area of research in the field of computer vision, enabling the generation of new images with different styles, textures, or resolutions while preserving their characteristic properties. Recent architectures leverage Generative Adversarial Networks (GANs) to transform input images from one domain to another. In this work, we focus on the study of both paired and unpaired image translation across multiple image domains. For the paired task, we used a conditional GAN model, and for the unpaired task, we trained it using cycle consistency loss. We experimented with different types of loss functions, multiple Patch-GAN sizes, and model architectures. New quantitative metrics - precision, recall, and FID score - were used for analysis. In addition, a qualitative study of the results of different experiments was conducted.