Methods and systems for determining estimation of motion of a device are provided. An example method includes receiving data from an inertial measurement unit (IMU) of a device and receiving images from a camera of the device for a sliding time window. The method also includes determining an IMU estimation of motion of the device based on the data from the IMU, and a camera estimation of motion of the device based on feature tracking in the images. The method includes, based on the IMU estimation and the camera estimation having a difference more than a threshold amount, determining one or more of a position or a velocity of the device for the sliding time window, and determining an overall estimation of motion of the device as supported by the data from the IMU and the position or velocity of the device.