Resumen
In this study, we propose a novel Temporal Development Generative Adversarial Network (TD-GAN) for the generation and analysis of videos, with a particular focus on biological and medical applications. Inspired by Progressive Growing GAN (PG-GAN) and Temporal GAN (T-GAN), our approach employs multiple discriminators to analyze generated videos at different resolutions and approaches. A new Temporal Discriminator (TD) that evaluates the developmental coherence of video content is introduced, ensuring that the generated image sequences follow a realistic order of stages. The proposed TD-GAN is evaluated on three datasets: Mold, Yeast, and Embryo, each with unique characteristics. Multiple evaluation metrics are used to comprehensively assess the generated videos, including the Fréchet Inception Distance (FID), Frechet Video Distance (FVD), class accuracy, order accuracy, and Mean Squared Error (MSE). Results indicate that TD-GAN significantly improves FVD scores, demonstrating its effectiveness in generating more coherent videos. It achieves competitive FID scores, particularly when selecting the appropriate number of classes for each dataset and resolution. Additionally, TD-GAN enhances class accuracy, order accuracy, and reduces MSE compared to the default model, demonstrating its ability to generate more realistic and coherent video sequences. Furthermore, our analysis of stage distribution in the generated videos shows that TD-GAN produces videos that closely match the real datasets, offering promising potential for generating and analyzing videos in different domains, including biology and medicine.