A 3D Shape Retrieval Framework Supporting Multimodal Queries

This paper presents a unified framework for 3D shape retrieval. The method supports multimodal queries (2D images, sketches, 3D objects) by introducing a novel view-based approach able to handle the different types of multimedia data. More specifically, 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 produced. The global shape similarity between two 3D models is achieved by applying a novel matching scheme, which effectively combines the information extracted from the multi-view representation. The experimental results prove that the proposed method demonstrates superior performance over other well-known state-of-the-art approaches. Keywords 3D object retrieval · Multi-views · Multimodal queries · Image to 3D object · Sketch to 3D object

• Type: Journal
• Year: 2010
• Where: IJCV
• Authors: Petros Daras, Apostolos Axenopoulos
• Keywords: Global Shape Similarity, IJCV 2010, Image, Rotation-invariant Shape Descriptors