A head-mounted display (HMD) device is disclosed. The HMD device includes a frame and a display system coupled to the frame. A stereo depth camera system coupled to the frame generates stereo depth camera information comprising frames of imagery and depth data that identifies a distance to a simulator cockpit of a simulator. A processor device is coupled to the stereo depth camera system and to the display system. The processor device identifies, based on the stereo depth camera information, a particular cockpit model that corresponds to the simulator cockpit and that identifies a layout of cockpit controls of the simulator cockpit. The processor device, based at least in part on the cockpit model and a physical location of the simulator cockpit, generates computer-generated imagery. The processor device sends the computer-generated imagery to the display system to overlay the computer-generated imagery on top of a portion of a real-world scene.