Abstract

An important task in ob ject recognition is to enable algo- rithms to categorize ob jects under arbitrary poses in a cluttered 3D world. A recent paper by Savarese & Fei-Fei [1] has proposed a novel representation to model 3D ob ject classes. In this representation sta- ble parts of ob jects from one class are linked together to capture both the appearance and shape properties of the ob ject class. We propose to extend this framework and improve the ability of the model to recog- nize poses that have not been seen in training. Inspired by works in single ob ject view synthesis (e.g., Seitz & Dyer [2]), our new represen- tation allows the model to synthesize novel views of an ob ject class at recognition time. This mechanism is incorporated in a novel two-step algorithm that is able to classify ob jects under arbitrary and/or unseen poses. We compare our results on pose categorization with the model and dataset presented in [1]. In a second experiment, we collect a new, more challenging dataset of 8 ob ject classes from crawling the web. In both experiments, our model shows competitive performances compared to [1] for classifying ob jects in unseen poses.