A proper extraction of internal tidal signals is central to the interpretation of Sea Surface Height (SSH) data, yet challenging in upcoming satellite missions, where traditional harmonic analysis may break down at finer observed spatial scales known to contain significant wave-mean interactions. However, the wide swaths featured in such satellite missions render SSH snapshots that are spatially two-dimensional, which allows us to treat the tidal extraction as an image translation problem. We design and train a conditional Generative Adversarial Network, which, given a snapshot of raw SSH from an idealized numerical eddying simulation, generates a snapshot of the embedded tidal component. We test it on synthetic data whose dynamical regimes are different from the data provided during training. Despite the diversity and complexity of data, it accurately extracts tidal components in most individual snapshots considered and reproduces physically meaningful statistical properties.