The subject technology receives image data including a representation of a physical item. The subject technology analyzes the image data to determine an object corresponding to the physical item. The subject technology extracts product metadata based on the determined object. The subject technology sends, to a server, the product metadata to determine second product metadata associated with the product metadata. The subject technology receives, from the server, the second product metadata, the second product metadata including additional information related to the physical item. The subject technology causes display, at a client device, the additional information related to the physical item based at least in part on the second product metadata.