A system for volume dimensioning via two-dimensional (2D)/three-dimensional (3D) sensor fusion, based in a tablet, phablet, or like mobile device, is disclosed. The mobile device includes a 2D imager for capturing an image stream of its field of view (FOV), the FOV including target objects. The mobile device includes a 3D imager for collecting 3D imaging data of the FOV including point clouds of each target object within the FOV. Processors of the mobile device positively identify a particular target object by correlating the 2D and 3D image streams and generating a holographic model of the target object overlaid on the video stream, with adjustable surface, edge, and vertex guides. The processors determine the precise dimensions of the target object by measuring the holographic model, and detect and decode object identifiers (2D or 3D) on the surface of the target object to acquire and supplement object data.