LATFormer: Locality-Aware Point-View Fusion Transformer for 3D shape recognition

Xinwei He, Silin Cheng, Dingkang Liang, Song Bai, Xi Wang, Yingying Zhu

Abstract: Highlights•We propose a Locality-Aware Fusion (LAF) module to fuse point clouds and images.•Based on LAF, we construct Locality-Aware Point-View Fusion Transformer.•Significant improvements over state-of-the-arts on 3D shape datasets are obtained.