Methods, systems, computer-readable media, and apparatuses are presented for generating a photorealistic viewable model using augmented reality (AR). An AR scene is generated by overlaying a virtual object onto a view of a physical environment. When placed into the AR scene, the virtual object can interact with the physical environment by, for example, reflecting or taking on colors, shadows, brightness, and other attributes of the physical environment. To generate the viewable model, the virtual object is manipulated (e.g., moved or rotated) within the AR scene and a plurality of images are generated by capturing the virtual object as the virtual object is being manipulated. The viewable model can be generated based on one or more of the images and can be output in the form of an interactive presentation, for example, a spin image.