Various implementations for detection and visualization of a formation of a tangible interface object include a method that includes capturing a video stream that includes an activity object and a formation of a tangible interface object, identifying the activity object, determining a virtual object based on the identity of the activity object, displaying a graphical user interface embodying a virtual scene and including the virtual object, detecting a formation of the tangible interface object, generating a virtualization based on the formation of the tangible interface object, and updating the graphical user interface to include the visualization.