In order to robustly perform SLAM (Simultaneous Localization and Mapping), places need to be recognized when they are visited again. In the deep-sea environment SLAM-assisted navigation based on side-scan sonar data benefits from using three-dimensional features of the environment as they are much less view-dependent than classic 2D features. Obtaining these features requires processing of the sonar data as the side-scan sonar sensor readings contain three dimensional information only indirectly. To extract that information the ensonification process needs to be inverted. This inversion is an ill-posed inverse problem and therefore regularization is needed before a unique solution can be found. Once the true seabed shape is reconstructed, wide area SLAM techniques can be applied.