A Compact Multi-view Descriptor for 3D Object Retrieval

摘要

In this paper, a novel view-based approach for 3D object retrieval is introduced. A set of 2D images (multi-views) are automatically generated from a 3D object, by taking views from uniformly distributed viewpoints. For each image, a set of 2D rotation-invariant shape descriptors is extracted. The global shape similarity between two 3D models is achieved by applying a novel matching scheme, which effectively combines the information extracted from the multiview representation. The proposed approach can well serve as a unified framework, supporting multimodal queries (such as sketches, 2D images, 3D objects). The experimental results illustrate the superiority of the method over similar view-based approaches.