View Synthesis for Recognizing Unseen Poses of Object Classes

An important task in object recognition is to enable algorithms to categorize objects under arbitrary poses in a cluttered 3D world. A recent paper by Savarese & Fei-Fei [1] has proposed a novel representation to model 3D object classes. In this representation stable parts of objects from one class are linked together to capture both the appearance and shape properties of the object class. We propose to extend this framework and improve the ability of the model to recognize poses that have not been seen in training. Inspired by works in single object view synthesis (e.g., Seitz & Dyer [2]), our new representation allows the model to synthesize novel views of an object class at recognition time. This mechanism is incorporated in a novel two-step algorithm that is able to classify objects 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 object classes from crawling the web. In both experiments, our model shows competitive performances compared to [1] for classifying objects in unseen poses.