Abstract
Most of the recent work on image-based ob ject recognition and 3D reconstruction has focused on improving the underlying algo- rithms. In this paper we present a method to automatically improve the quality of the reference database, which, as we will show, also af- fects recognition and reconstruction performances significantly. Starting out from a reference database of clustered images we expand small clus- ters. This is done by exploiting cross-media information, which allows for crawling of additional images. For large clusters redundant information is removed by scene analysis. We show how these techniques make ob ject recognition and 3D reconstruction both more efficient and more precise - we observed up to 14.8% improvement for the recognition task. Fur- thermore, the methods are completely data-driven and fully automatic.