The goal of a SLAM (Simultaneous Localization and Mapping) system is to estimate the camera s trajectory in space while reconstructing an accurate map of the surrounding environment. Its definition can be explained in two parts: the first one, mapping an unknown environment, and the second, performing agent localization in this environment through available sensors. Among the different types of sensors, cameras have lower operating costs while providing a rich amount of environmental information that allows for more precise mapping. Because of this, solutions where only the use of the camera is employed as the main sensor, called Visual SLAM Systems, are of great interest. This work proposes an adaptation of a Visual SLAM System that uses Visual Foundation Models to generate depth images that assist in the robustness of mapping and localization in the environment. Additionally, such a system should also be capable of identifying dynamic elements in the environment and removing them from the map, through the use of computer vision models. Finally, this should be viable for real-time applications.