Local geometry-perceptive mesh convolution with multi-ring receptive field

Shanghuan Liu, Xunhao Chen, Shaoyan Gai, Feipeng Da

Abstract: Highlights•Utilizing local irregular mesh structures, dynamic neighbor-attention weights of template’s nodes perceive local mesh change information of different vertices.•Multiple attention aggregations and shared anisotropic filters help extract geometry features of large local receptive fields with multi-ring.•The proposed method determines our deep 3D morphable models (3DMMs) have smaller sizes than previous models and achieve state-of-the-art performances.