A mobile platform renders different augmented reality objects based on the spatial relationship, such as the proximity and/or relative positions between real-world objects. The mobile platform detects and tracks a first object and a second object in one or more captured images. The mobile platform determines the spatial relationship of the objects, e.g., the proximity or distance between objects and/or the relative positions between objects. The proximity may be based on whether the objects appear in the same image or the distance between the objects. Based on the spatial relationship of the objects, the augmentation object to be rendered is determined, e.g., by searching a database. The selected augmentation object is rendered and displayed.