Improved Panoramic Representation via Bidirectional Recurrent View Aggregation for Three-Dimensional Model Retrieval

• Published in: IEEE computer graphics and applications 2019-03, Vol.39 (2), p.65-76
• Main Authors: Xu, Cheng, Zhang, Cheng, Zhou, Xiaochen, Leng, Biao
• Format: Magazinearticle
• Language: English
• Subjects: Artificial neural networks; Cameras; Computational modeling; Feature extraction; Representations; Retrieval; Shape; Shape memory; Shape recognition; Solid modeling; Three dimensional models; Three-dimensional displays; Two dimensional displays
• ISSN: 0272-1716; 1558-1756
• DOI: 10.1109/MCG.2018.2884861

In a view-based three-dimensional (3-D) model retrieval task, extracting discriminative high-level features of models from projected images is considered as an effective approach. The challenge of view-based 3-D shape retrieval is that the shape information of each view is limited due to information deficiency in projection. Traditional methods in this direction mostly convert the model into a panoramic view, making it hard to recognize the original shape. To resolve this problem, we propose a novel deep neural network, recurrent panorama network (RePanoNet), which can learn to build panoramic representation from view sequences. A view sequence is rendered at a circle around the model to provide enough panoramic information. For each view sequence, we employ the bidirectional long short-term memory in RePanoNet to recognize spatial correlations between adjacent views to construct a panoramic feature. In our experiments on ModelNet and ShapeNet Core55, RePanoNet outperforms the methods in the state of the art, which demonstrates its effectiveness.