A medical visualization apparatus includes two or more imaging devices, two or more robotic arms, multiple magnetic sensors coupled with the imaging devices, and a processor. The two or more imaging devices are configured to acquire images of an organ of a patient. The two or more robotic arms are configured to move the respective imaging devices. The multiple magnetic sensors are configured to output, in response to a magnetic field of a position tracking system, signals indicative of positions and viewing directions of the imaging devices. The processor is configured to estimate a position and a viewing direction of each of the imaging devices based on the signals, and, using the estimated positions and viewing directions, combine the images of the organ acquired by the imaging devices into a virtual reality (VR) image of the organ, and present the VR image to a user on a VR viewer.