LIMAN: Local Information-Based Multiattention Network for 3D Shape Recognition

Exploring effective 3D shape recognition algorithms attracts much research attention recently. The existing multiview-based 3D shape recognition methods usually ignore the local information exploration in each view image. In this article, we propose a novel local information-based multiattention network, which concentrates the effective information in the feature maps and captures the view-wise interactions to improve the shape representation performance. Concretely, we design the spatial-aware and channel-aware weight learning modules to quantify the contributions of each spatial region and channel for feature map updating in the view-wise descriptor extraction process. Then, the multihead attention module is introduced for multiview feature aggregation, considering the view-wise interactions to preserve the effective information. Finally, we generate the discriminative shape descriptors for 3D shape recognition task. We conduct comprehensive experiments on the ModelNet databases and achieve competitive performances compared with the state-of-the-art methods.